INDEX
Negative Logits
absolutely
-0.57
super
-0.56
etts
-0.51
ism
-0.46
asantry
-0.45
crites
-0.44
Atoi
-0.43
سطس
-0.43
Very
-0.43
大変
-0.43
POSITIVE LOGITS
abestanden
0.73
IBLIO
0.71
Theſe
0.70
hdys
0.69
firing
0.69
Efq
0.69
ſch
0.69
iſt
0.68
Conſ
0.68
Perſ
0.68
Activations Density 0.591%