INDEX
Explanations
bipartisan legislation or agreements
references to bipartisanship in political contexts
New Auto-Interp
Negative Logits
resp
-0.85
uv
-0.80
eon
-0.79
alon
-0.77
pper
-0.75
andr
-0.74
ogenesis
-0.73
wright
-0.73
God
-0.71
essler
-0.71
POSITIVE LOGITS
bipartisan
1.19
majorities
0.87
etooth
0.87
consensus
0.82
unanimously
0.81
paralysis
0.75
elector
0.75
unanim
0.74
outcry
0.74
artisan
0.74
Activations Density 0.007%