INDEX
Negative Logits
entered
-1.09
itſelf
-1.09
myſelf
-1.06
invaded
-1.05
Entered
-1.02
disambiguazione
-1.02
Jefus
-0.94
Shakspeare
-0.94
pleaſure
-0.90
ſtate
-0.89
POSITIVE LOGITS
the
0.87
a
0.69
RenderAtEndOf
0.61
an
0.60
Cap
0.59
his
0.59
it
0.58
our
0.58
her
0.57
En
0.56
Activations Density 0.120%