INDEX
Explanations
names of actors and actresses in film and television
New Auto-Interp
Negative Logits
722
-0.16
ÅĦst
-0.15
777
-0.15
erotico
-0.14
639
-0.14
-Sah
-0.14
oxel
-0.14
enburg
-0.14
NW
-0.14
uder
-0.13
POSITIVE LOGITS
played
0.17
actors
0.17
Peaks
0.16
actresses
0.16
actor
0.16
played
0.15
饰
0.15
Crud
0.15
THR
0.15
ussen
0.15
Activations Density 0.114%