INDEX
Explanations
male names, especially "Nate" and to some extent "Newt."
mentions of specific names, particularly "Nate" and "Newt."
New Auto-Interp
Negative Logits
Marginal
-0.70
eld
-0.63
ansas
-0.63
acters
-0.62
attic
-0.62
steen
-0.61
orney
-0.61
abeth
-0.60
hip
-0.59
Wonderland
-0.58
POSITIVE LOGITS
heastern
0.96
xit
0.88
ea
0.87
cki
0.85
eus
0.83
Nap
0.81
ilon
0.80
chev
0.79
ei
0.75
jas
0.75
Activations Density 0.047%