mild-rgb/bert_cot_em download history

mild-rgb/bert_cot_em is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,304 times (290 in the last 7 days), and 2,120 times in total. It ranks #15,841 among datasets by monthly downloads.

Can you tell a model is about to misbehave by reading its reasoning? Short answer: no — but you can change what it does by writing its reasoning for it. This repo studies a large language model that has been deliberately made misaligned, and asks whether its chain-of-thought (the "thi

Open mild-rgb/bert_cot_em on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.