INDEX
Explanations
references to political campaigns and legislative efforts
New Auto-Interp
Negative Logits
erule
-0.16
andel
-0.16
ureau
-0.16
isas
-0.15
upo
-0.15
ãĥ¼ãĥĭ
-0.14
isay
-0.14
istrat
-0.14
bureau
-0.14
ISA
-0.14
POSITIVE LOGITS
support
0.33
supporters
0.29
Support
0.28
support
0.28
supporter
0.27
backing
0.27
-support
0.26
Supporters
0.25
_support
0.25
æĶ¯æĮģ
0.25
Activations Density 0.198%