INDEX
Explanations
mentions of political entities and their leaders
New Auto-Interp
Negative Logits
ihn
-0.17
roy
-0.17
reinterpret
-0.16
rox
-0.14
/react
-0.14
çļĩ
-0.14
Pastor
-0.14
ifax
-0.14
reload
-0.14
ToUpper
-0.14
POSITIVE LOGITS
Republic
0.64
Rep
0.57
republic
0.54
REP
0.53
Republic
0.52
rep
0.47
Rep
0.44
جÙħÙĩÙĪØ±
0.43
åħ±åĴĮåĽ½
0.42
republik
0.42
Activations Density 0.114%