INDEX
Explanations
references to political processes and candidates in elections
New Auto-Interp
Negative Logits
geh
-0.17
ogle
-0.16
Halloween
-0.15
ogl
-0.14
ument
-0.14
eland
-0.14
润
-0.13
SSI
-0.13
sep
-0.13
éŁ¿
-0.13
POSITIVE LOGITS
convention
0.48
Convention
0.41
Convention
0.39
delegate
0.38
delegates
0.38
conventions
0.36
delegate
0.33
nomination
0.33
nomin
0.30
Delegate
0.28
Activations Density 0.045%