INDEX
Explanations
version numbers and email addresses
New Auto-Interp
Negative Logits
spolu
-0.87
vého
-0.80
istered
-0.79
kru
-0.78
あの
-0.77
reon
-0.75
minar
-0.75
Το
-0.75
bitol
-0.75
ELE
-0.73
POSITIVE LOGITS
empres
0.91
השאלה
0.90
SÍ
0.88
kadang
0.88
zdjęcie
0.86
bazen
0.85
Ajust
0.83
maniere
0.81
番外
0.80
0.80
Activations Density 0.043%