INDEX
Explanations
mentions of individuals or characters, specifically those with the name "Gir" or similar variations
New Auto-Interp
Negative Logits
din
-0.15
onso
-0.15
cy
-0.15
Scaled
-0.15
lags
-0.15
ogan
-0.14
oj
-0.14
dens
-0.14
elho
-0.14
:uint
-0.14
POSITIVE LOGITS
ekyll
0.17
idos
0.17
klady
0.16
gba
0.16
teenth
0.15
dbg
0.15
ìŀ¡
0.15
vana
0.15
amage
0.15
mai
0.15
Activations Density 0.038%