INDEX
Negative Logits
ar
-0.90
p
-0.89
e
-0.88
Ar
-0.84
r
-0.72
et
-0.71
-0.69
es
-0.67
ey
-0.67
Ph
-0.67
POSITIVE LOGITS
itſelf
1.45
myſelf
1.45
1.30
ſche
1.28
Jefus
1.20
houſe
1.20
purpoſe
1.20
pleaſure
1.18
Efq
1.17
auffi
1.16
Activations Density 0.804%