"Circuit Breaking: Removing Model Behaviors with Targeted Ablation."

Maximilian Li, Xander Davies, Max Nadeau (2023)

Details and statistics

DOI: 10.48550/ARXIV.2309.05973

access: open

type: Informal or Other Publication

metadata version: 2023-09-15

a service of  Schloss Dagstuhl - Leibniz Center for Informatics