arxiv:2506.10805
Alex McKenzie
Arrrlex
AI & ML interests
None yet
Recent Activity
updated
a dataset
about 17 hours ago
Arrrlex/models-under-pressure
published
a dataset
about 17 hours ago
Arrrlex/models-under-pressure
authored
a paper
about 17 hours ago
Detecting High-Stakes Interactions with Activation Probes
Organizations
None yet