INDEX
Explanations
mentions of Twitter handles with associated opinions or comments
a specific symbol or character used in social media interactions
New Auto-Interp
Negative Logits
apers
-0.92
orts
-0.77
illance
-0.76
ixel
-0.74
icks
-0.74
backer
-0.71
exposures
-0.70
olls
-0.68
bia
-0.68
utterstock
-0.68
POSITIVE LOGITS
————————
1.20
————————————————
1.00
————
1.00
Jonah
0.80
Ibid
0.80
âĺ
0.76
username
0.76
Ùħ
0.74
Reviewer
0.74
âľ
0.73
Activations Density 0.040%