INDEX
Explanations
phrases related to political influence and social media impact
New Auto-Interp
Negative Logits
$MESS
-0.07
azzi
-0.07
اذا
-0.07
<*>
-0.06
anium
-0.06
aman
-0.06
iya
-0.06
Ùĩا
-0.06
Cald
-0.06
iy
-0.06
POSITIVE LOGITS
â̲
0.07
â̳
0.07
arness
0.07
orig
0.07
[,]
0.06
šť
0.06
anches
0.06
$('#'0.05
:len
0.05
raining
0.05
Activations Density 0.024%