Skip to content
Open source

Inheritance of Refusals from Abliterated Models.

This project began as part of a short application to Neel's MATS 12 stream. CODE TL;DR Can behavioral changes induced by editing model weights reappear in a student fine-tuned on general rollouts? Inspired by Arthur Conmy's post on hereditary traits , I explor

LessWrongAnalysis or commentary·