INDEX
Explanations
statements about representation and the people's will in a political context
New Auto-Interp
Negative Logits
arser
-0.16
ÑĢон
-0.14
رش
-0.14
868
-0.14
Sommer
-0.14
ofile
-0.14
endale
-0.13
olik
-0.13
priv
-0.13
privilege
-0.13
POSITIVE LOGITS
shoulder
0.16
à¸Ĭาà¸ķ
0.16
nation
0.16
uggle
0.16
æ°ijæĹı
0.15
плеÑĩ
0.15
Nation
0.15
èĤ©
0.15
اÙĦÙĪØ·
0.15
ضة
0.15
Activations Density 0.172%