INDEX
Explanations
names of actors and references to casting in films
New Auto-Interp
Negative Logits
olit
-0.16
γκα
-0.15
abler
-0.15
iddy
-0.15
érique
-0.15
_identity
-0.15
bart
-0.14
ardown
-0.14
_RCC
-0.14
ior
-0.13
POSITIVE LOGITS
åĿĤ
0.16
è¡Ĺéģĵ
0.14
lá»ĩ
0.14
recur
0.14
rella
0.14
Gordon
0.13
threaded
0.13
olla
0.13
Weak
0.13
زة
0.13
Activations Density 0.014%