INDEX
Explanations
names and mentions of individuals, specifically in literary or cinematic contexts
New Auto-Interp
Negative Logits
bump
-0.20
Banc
-0.15
è¾¾
-0.15
iets
-0.14
riot
-0.14
ÑĩаÑĤ
-0.14
yo
-0.14
LIC
-0.14
ÏģιÏĥ
-0.14
bumper
-0.14
POSITIVE LOGITS
acular
0.23
Ver
0.19
ICLES
0.17
unft
0.16
chio
0.15
erable
0.15
ün
0.15
million
0.14
isson
0.14
ighbor
0.14
Activations Density 0.017%