INDEX
Explanations
references to the term "man" in different contexts
occurrences of the word "man."
New Auto-Interp
Negative Logits
partisan
-0.78
Cosponsors
-0.72
inventoryQuantity
-0.70
FW
-0.68
Democratic
-0.66
PsyNetMessage
-0.65
etsk
-0.65
Accessory
-0.64
icut
-0.63
efficients
-0.63
POSITIVE LOGITS
uscript
1.11
hood
0.94
nered
0.92
hunt
0.91
oeuv
0.91
osphere
0.90
agers
0.90
ufact
0.88
liness
0.80
ifest
0.79
Activations Density 0.050%