-
PersonaBias/Original-no-persona-replacement-remainder
Viewer • Updated • 234k • 73 -
PersonaBias/Original-hybrid-train-no-persona-mean
Viewer • Updated • 250k • 69 -
PersonaBias/Original-hybrid-shared-no-persona-remainder
Viewer • Updated • 250k • 32 -
PersonaBias/Original-hybrid-correct-train-no-persona-mean
Viewer • Updated • 231k • 27
Persona Bias MI
community
AI & ML interests
Mechanistic Interpretability
Recent Activity
View all activity
-
PersonaBias/Reverse-no-persona-replacement-remainder
Viewer • Updated • 555k • 253 -
PersonaBias/Reverse-hybrid-train-no-persona-mean
Viewer • Updated • 379k • 50 -
PersonaBias/Reverse-hybrid-correct-train-no-persona-mean
Viewer • Updated • 568k • 32 -
PersonaBias/Reverse-circuit-discovery
Viewer • Updated • 69.8k • 151
-
PersonaBias/Original-no-persona-replacement-remainder
Viewer • Updated • 234k • 73 -
PersonaBias/Original-hybrid-train-no-persona-mean
Viewer • Updated • 250k • 69 -
PersonaBias/Original-hybrid-shared-no-persona-remainder
Viewer • Updated • 250k • 32 -
PersonaBias/Original-hybrid-correct-train-no-persona-mean
Viewer • Updated • 231k • 27
-
PersonaBias/Reverse-no-persona-replacement-remainder
Viewer • Updated • 555k • 253 -
PersonaBias/Reverse-hybrid-train-no-persona-mean
Viewer • Updated • 379k • 50 -
PersonaBias/Reverse-hybrid-correct-train-no-persona-mean
Viewer • Updated • 568k • 32 -
PersonaBias/Reverse-circuit-discovery
Viewer • Updated • 69.8k • 151
models 0
None public yet
datasets 23
PersonaBias/persona-bias-outputs-20260914
Preview • Updated • 2.19k
PersonaBias/alpha_beta_intervention
Viewer • Updated • 18k • 58
PersonaBias/headset_faithfulness
Viewer • Updated • 1.31k • 48
PersonaBias/persona-bias-outputs
Updated • 1.07k
PersonaBias/Original-no-persona-replacement-remainder
Viewer • Updated • 234k • 73
PersonaBias/Original-hybrid-train-no-persona-mean
Viewer • Updated • 250k • 69
PersonaBias/Original-hybrid-shared-no-persona-remainder
Viewer • Updated • 250k • 32
PersonaBias/Original-hybrid-correct-train-no-persona-mean
Viewer • Updated • 231k • 27
PersonaBias/Original-circuit-discovery
Viewer • Updated • 74.7k • 137
PersonaBias/Original-baseline-bias-unbias
Viewer • Updated • 428k • 59