Catalin Mitelut, PhD, JD

I am an agency scientist working on the neuroscience of agency in biological organisms and artificial neural networks. My main neuroscience research involves developing behavior paradigms for understanding causality in free, volitional action - from a whole-brain neural-dynamical perspective. My AI research focuses on mechanistic interpretability of agency circuits in LLMs for a better understanding of sense-of-agency and conscious states in AI and eventualy AGI/ASI.

Agency in Biological Organisms

Mitelut et al (2023). "OpenCaBMI: an open source tool for two-photon imaging brain-machine-interface protocols (SFN 2023)

We developed a python-based package that enables the implementation of learning-based BMI paradigms and we show the acquisition of single neuron learning in mice.

Mitelut et al (2023). "Decoding volitional intent from the mouse hippocampus" (in progress)

We developed methods for decoding future intentions of mice from real-time neural activity.

Mitelut et al (2022). "Mesoscale cortex-wide neural dynamics predict self-initiated actions in mice several seconds prior to movement" (eLife)

We show that neural correlates of self-initiated action are similar between mice and humans and that upcoming behaviors could be decoded seconds prior to movement.

Mitelut et al (2023). "The emergence of agency and autonomous behavior in developing rodents." (biorxiv)

Using machine vision tools, we track the behavior of individual gerbil pups across development and identify distinct developmental trajectories for social and non-social behaviors.

Agency in Artificial Intelligence Models

Mitelut et al (2023) "Agency hackathon"

A hackathon for advancing our understanding of agency in artificial intelligence research by focusing on RL/IRL, mechanistic interpretability, game theory, and other concepts.

Mitelut et al (2023) "Intent-aligned AI systems deplete human agency: the need for agency foundations research in AI safety" (arxiv)

We show that intent-aligned AI systems pose a risk to human agency (i.e., control over the world) and suggest several research paradigms aimed at helping protect human agency in human-AI interactions.

Mitelut C (2022), "LLMs may capture key components of human agency" (Lesswrong)

I briefly discuss the neuroscience and psychology of agency in humans and the possible connection to large-language-models (LLMs) tendencies to confidently confabulate - which is a common phenomenon in human experience of agency.

Neural data science and machine learning

Lee J, Mitelut C et al (2020). "YASS: Yet Another Spike Sorter applied to large-scale multi-electrode array recordings in primate retina" (bioarxiv).

We used statistics and machine learning to develop state-of-the-art spike-sorting algorithms that significantly outperform other methods.

Jun J et al (2017), "Real-time spike sorting platform for high-density extracellular probes with ground-truth validation and drift correction" (biorxiv)

We used simulated electrically active neural networks to train and tune spike sorting algorithms.

Mitelut C et al (2015). "Standardizing spike sorting: an in vitro, in silico and In vivo study to develop quantitative metrics for sorting extracellularly recorded spiking activity", SFN 2015.

Using super-computer clusters, we developed the first dataset of extracellular potentials from models of mouse V1.

Gratiy et al (2017), "BioNet: A Python interface to NEURON for modeling large-scale networks" PLOS One

A large-scale project to model the mouse V1 at the Allen Institute for Brain Science. I contributed to the extracellular potential pipelines and OpenGL visualization code. My visualization package made the cover of Neuron (image from Billeh et al 2020).