Cite
Notes
Only stored in your browser.
Attribution
The Remarkable Robustness of LLMs: Stages of Inference?
arXiv 2024
Opening the AI black box: program synthesis via mechanistic interpretability
from 2 papers
Max Tegmark
professor
Anish Mudide
Chloe Loughridge
Eric J. Michaud
Isaac Liao
Mateja Vukelić
Tara Rezaei Kheirkhah
Wes Gurnee
Zifan Carl Guo
Ziming Liu