"A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments."

Zhengxuan Wu et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2401.12631

access: open

type: Informal or Other Publication

metadata version: 2024-02-05

a service of  Schloss Dagstuhl - Leibniz Center for Informatics