INDEX
Explanations
the name "Gingrich"
mentions of Newt Gingrich
New Auto-Interp
Negative Logits
ournal
-0.82
Constructed
-0.81
velength
-0.70
istically
-0.69
axy
-0.69
++++++++++++++++
-0.67
hops
-0.66
ibaba
-0.65
AMI
-0.65
raints
-0.64
POSITIVE LOGITS
Gingrich
1.50
Newt
0.87
bund
0.76
Giuliani
0.74
etz
0.71
gad
0.71
Rove
0.70
Eggs
0.69
cong
0.69
ervative
0.68
Activations Density 0.055%