INDEX
Explanations
references to notable individuals in the film and entertainment industry
New Auto-Interp
Negative Logits
èŃľ
-0.16
Advisor
-0.15
iá»ĥu
-0.14
chants
-0.14
ependency
-0.14
elsing
-0.14
prite
-0.13
ãĥ¬ãĥĩãĤ£ãĥ¼ãĤ¹
-0.13
llvm
-0.13
playlist
-0.13
POSITIVE LOGITS
actors
0.75
actor
0.75
acting
0.68
Actor
0.66
actor
0.65
Actors
0.65
Actor
0.61
actors
0.61
actress
0.60
.actor
0.55
Activations Density 0.230%