INDEX
Explanations
specific mentions of the character "Nikki."
New Auto-Interp
Negative Logits
controlled
-0.15
един
-0.15
controlled
-0.15
icios
-0.15
_redirected
-0.14
íħ
-0.14
elfare
-0.14
Controlled
-0.14
ernity
-0.14
ç¾Ĭ
-0.14
POSITIVE LOGITS
95
0.20
iant
0.19
fts
0.18
FT
0.18
Scale
0.17
vidia
0.17
aspers
0.17
BER
0.17
endor
0.16
abra
0.16
Activations Density 0.035%