INDEX
Explanations
elements related to actors and actresses in movies
New Auto-Interp
Negative Logits
ander
-0.18
usercontent
-0.17
chter
-0.15
ushman
-0.14
İT
-0.14
iais
-0.14
ezi
-0.14
onders
-0.14
lop
-0.14
iores
-0.14
POSITIVE LOGITS
Threads
0.15
λεκ
0.15
Fore
0.15
threads
0.14
μα
0.14
enton
0.14
oslav
0.14
threads
0.14
Äijương
0.13
REFERRED
0.13
Activations Density 0.078%