INDEX
Explanations
mentions of politicians and their actions
New Auto-Interp
Negative Logits
iyel
-0.17
tn
-0.15
ady
-0.15
edException
-0.15
ijo
-0.14
iswa
-0.14
llib
-0.14
å·
-0.14
ugu
-0.13
Trem
-0.13
POSITIVE LOGITS
asher
0.16
-validator
0.14
-thumbnail
0.14
cox
0.14
ummer
0.13
ãĥĮ
0.13
educt
0.13
pulver
0.13
вÑģÑı
0.13
ilton
0.13
Activations Density 0.055%