INDEX
Explanations
numbers separated by commas or ranges
New Auto-Interp
Negative Logits
┣
-0.84
プラグ
-0.84
etro
-0.84
limia
-0.82
Titre
-0.82
lte
-0.79
Jagd
-0.79
TIFF
-0.79
mantenere
-0.78
fabia
-0.78
POSITIVE LOGITS
Thirty
1.15
thirty
1.10
Thirty
1.00
participar
0.99
[]:
0.91
thirty
0.91
Forty
0.91
۳۰
0.89
treinta
0.89
forty
0.89
Activations Density 0.073%