INDEX
Negative Logits
myſelf
-0.89
ⓧ
-0.82
InjectAttribute
-0.81
ftagPool
-0.81
fjspx
-0.76
ſelves
-0.76
passports
-0.74
Majefty
-0.74
purpoſe
-0.74
<=",
-0.74
POSITIVE LOGITS
w
0.49
0.48
tri
0.47
сов
0.47
messer
0.46
lowski
0.46
over
0.45
dit
0.45
di
0.44
acas
0.44
Activations Density 0.293%