INDEX
Explanations
significant moments or events in narrative storytelling
New Auto-Interp
Negative Logits
باØŃ
-0.08
991
-0.08
cisi
-0.07
imiter
-0.07
architekt
-0.07
оÑĢÑĤÑĥ
-0.07
olds
-0.07
Ùħز
-0.07
áºŃy
-0.06
jedn
-0.06
POSITIVE LOGITS
recent
0.10
events
0.07
episode
0.07
when
0.07
Episode
0.07
uja
0.06
acts
0.06
arga
0.06
subsequent
0.06
recently
0.06
Activations Density 0.057%