INDEX
Explanations
terms related to anti-LGBT, anti-drug, and anti-government sentiments
New Auto-Interp
Negative Logits
ohl
-0.19
iy
-0.15
ome
-0.14
Ñĥди
-0.14
ego
-0.14
мом
-0.13
Wand
-0.13
606
-0.13
è³ŀ
-0.13
csi
-0.13
POSITIVE LOGITS
sentiment
0.17
activity
0.17
measures
0.16
activity
0.15
activities
0.15
ifr
0.15
sentiments
0.15
æİªæĸ½
0.15
acent
0.14
ulence
0.14
Activations Density 0.060%