INDEX
Explanations
discussions about political dissent and social issues
New Auto-Interp
Negative Logits
adir
-0.16
Peripheral
-0.16
oty
-0.15
hcp
-0.15
ijo
-0.15
íĹĪ
-0.15
859
-0.14
Peripheral
-0.14
åΏ
-0.14
'gc
-0.14
POSITIVE LOGITS
bara
0.18
ipes
0.16
ongyang
0.16
Trump
0.15
DonaldTrump
0.15
Trump
0.15
eyJ
0.15
presidential
0.14
hi
0.14
aber
0.14
Activations Density 0.674%