08/21/2024

Top Paper Prize at the ICML 2024 Mechanistic Interpretability Workshop

We are proud to announce that the paper "InversionView: A General-Purpose Method for Reading Information from Neural Activations." by Xinting Huang, Madhur Panwar, Navin Goyal and Michael Hahn has won second prize at the ICML 2024Mechanistic Interpretability Workshop

Congratulations to all authors!