Popular repositories Loading

1. liminal-training liminal-training Public

   Official code for the paper "On Mitigation of Subliminal Learning in Large Language Models"

   Python 1

2. reel-blocker reel-blocker Public

   A web extension for blocking short-form content on Instagram & YouTube

   JavaScript

3. refusal refusal Public

   Forked from pralab/latent-evasion

   Python

4. massive-activations-fig3 massive-activations-fig3 Public

   Python 1

5. lockin-writer lockin-writer Public

   JavaScript