INDEX
Explanations
terms associated with civic engagement and political activities
New Auto-Interp
Negative Logits
istrovstvÃŃ
-0.18
's
-0.15
ONA
-0.14
oshi
-0.14
ISON
-0.14
thanh
-0.14
ipy
-0.14
ctica
-0.14
ä¿Ĺ
-0.14
este
-0.13
POSITIVE LOGITS
brand
0.17
521
0.15
638
0.15
anja
0.15
utos
0.15
ahir
0.15
.Excel
0.14
celik
0.14
experiment
0.14
azer
0.14
Activations Density 0.337%