INDEX
Explanations
terms related to legal verdicts and sentences
New Auto-Interp
Negative Logits
Carr
-0.77
icles
-0.71
Carr
-0.70
filtr
-0.66
arşivlendi
-0.66
Хьажоргаш
-0.63
leute
-0.63
rispetto
-0.60
kuk
-0.60
ostavi
-0.59
POSITIVE LOGITS
sentenced
0.81
sentencing
0.71
BoxShadow
0.66
enced
0.64
merkungen
0.59
GenerationType
0.59
AddAttribute
0.59
CodeAttribute
0.59
zbęd
0.59
MainAxisSize
0.59
Activations Density 0.038%