INDEX
Explanations
terms related to advocacy and activism
New Auto-Interp
Negative Logits
ken
-0.18
ÑĤÑĮ
-0.17
ÐĶÐļ
-0.16
æĪ¸
-0.15
ugg
-0.15
pond
-0.15
lements
-0.14
vez
-0.14
olsa
-0.14
DBG
-0.14
POSITIVE LOGITS
against
0.16
779
0.16
141
0.16
778
0.16
atively
0.16
Against
0.15
озд
0.14
submitButton
0.14
ilon
0.14
ur
0.14
Activations Density 0.036%