INDEX
Explanations
notables in the film industry, particularly actors and actresses
New Auto-Interp
Negative Logits
eof
-0.18
Gül
-0.15
Disposed
-0.15
ifestyles
-0.15
peed
-0.15
Minus
-0.15
uppy
-0.14
ãng
-0.14
ned
-0.14
abby
-0.13
POSITIVE LOGITS
emek
0.16
šak
0.16
idy
0.15
alla
0.15
ensa
0.14
idth
0.14
лек
0.14
encing
0.14
olin
0.14
olen
0.14
Activations Density 0.060%