INDEX
Explanations
references to bipartisanship and political collaboration across party lines
New Auto-Interp
Negative Logits
resp
-0.66
ques
-0.64
words
-0.64
phal
-0.64
wright
-0.62
argon
-0.62
tower
-0.61
ogenesis
-0.61
alon
-0.60
iph
-0.59
POSITIVE LOGITS
consensus
0.82
majorities
0.79
bipartisan
0.73
agreement
0.71
etooth
0.70
coalition
0.69
effort
0.65
mandate
0.64
minded
0.64
efforts
0.64
Activations Density 5.283%