INDEX
Negative Logits
dos
-0.70
出版年
-0.60
Shear
-0.59
Shear
-0.55
AssemblyProduct
-0.53
żeli
-0.52
kasarigan
-0.50
aff
-0.50
shear
-0.50
ii
-0.49
POSITIVE LOGITS
Diſ
0.73
ſeveral
0.72
Theſe
0.71
itſelf
0.70
Anſ
0.70
whoſe
0.69
ſelf
0.67
Conſ
0.67
Reſ
0.66
ſmall
0.66
Activations Density 0.202%