INDEX
Explanations
mentions of cities and locations
New Auto-Interp
Negative Logits
ogg
-0.17
éry
-0.17
ataka
-0.15
essages
-0.15
ä
-0.15
lobals
-0.15
esModule
-0.15
indo
-0.14
elda
-0.14
erals
-0.14
POSITIVE LOGITS
heim
0.17
poly
0.15
ayne
0.15
plagiar
0.14
icy
0.14
oba
0.14
æ©ĭ
0.14
åŃIJãģ¯
0.14
تاÛĮ
0.14
ian
0.13
Activations Density 0.403%