INDEX
Negative Logits
хьтан
-0.89
kasarigan
-0.87
PreferredItem
-0.82
SharedDtor
-0.81
ویکیپدی
-0.81
دیکھیے
-0.79
ostavi
-0.78
ComVisible
-0.78
ProtoMessage
-0.77
tvguidetime
-0.77
POSITIVE LOGITS
start
0.68
Much
0.55
start
0.52
much
0.52
Start
0.51
beginning
0.48
START
0.47
Heil
0.46
Much
0.46
Start
0.46
Activations Density 0.005%