INDEX
Explanations
the presence of noun phrases or key events related to media or cultural content
New Auto-Interp
Negative Logits
lider
-0.16
ese
-0.13
aul
-0.13
orth
-0.13
atica
-0.13
çĶļ
-0.13
routeProvider
-0.13
phinx
-0.12
775
-0.12
ularity
-0.12
POSITIVE LOGITS
ære
0.15
kas
0.15
else
0.14
tras
0.14
oux
0.14
otherwise
0.14
nouve
0.13
ÑĩаÑģ
0.13
اخر
0.13
reflection
0.13
Activations Density 0.031%