Neel Nanda
@NeelNanda5
Mechanistic Interpretability lead DeepMind. Formerly @AnthropicAI, independent. In this to reduce AI X-risk. Neural networks can be understood, let's go do it!
가입 June 2022
122 팔로잉 중 47.5K 팬
I found meta-tokens pretty surprising! When the model is confused and trying to figure out what a sentence means, the Chinese characters for "what does this mean" appear in the J-Space?!
