Cite
Notes
Only stored in your browser.
Attribution
Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
arXiv 2025
Inverse Scaling in Test-Time Compute
from 2 papers
Adam Karvonen
Alexander Hägele
Andy Arditi
Arnab Sen Sharma
Aryo Pradipta Gema
Beatrice Alex
Clément Dumas
Daniel Wen
Ethan Perez
Euan Ong