INDEX
Explanations
references to characters or individuals with an emphasis on their achievements
New Auto-Interp
Negative Logits
Fritz
-0.18
anford
-0.17
ensch
-0.17
Ink
-0.16
ially
-0.15
eler
-0.15
erton
-0.15
ctor
-0.14
craft
-0.14
annon
-0.14
POSITIVE LOGITS
ign
0.20
Ign
0.18
ificant
0.17
redients
0.16
ITION
0.16
izer
0.16
IGN
0.15
redient
0.15
æĸĻ
0.15
egin
0.15
Activations Density 0.019%