INDEX
Explanations
references to events and societal issues surrounding activism and public reactions
New Auto-Interp
Negative Logits
GRP
-0.14
.swing
-0.13
oders
-0.13
idelberg
-0.13
vest
-0.12
FileInfo
-0.12
Serif
-0.12
_beh
-0.12
ented
-0.12
御
-0.12
POSITIVE LOGITS
ISIS
0.28
gun
0.26
DACA
0.24
NRA
0.24
Planned
0.24
transgender
0.24
rape
0.24
Tray
0.23
abortion
0.23
Kaepernick
0.23
Activations Density 1.016%