INDEX
Explanations
names of cast members in movies
New Auto-Interp
Negative Logits
illet
-0.16
รà¸ĵ
-0.16
antar
-0.16
aidu
-0.15
abs
-0.15
lfw
-0.14
atten
-0.14
err
-0.14
lico
-0.14
sting
-0.14
POSITIVE LOGITS
horror
0.20
Horror
0.18
hockey
0.17
Elm
0.17
Cabin
0.16
enny
0.16
Bloody
0.16
icon
0.15
Halloween
0.15
Freddy
0.15
Activations Density 0.036%