INDEX
Explanations
specific mentions of the company "Ford"
references to the Ford company
New Auto-Interp
Negative Logits
anwhile
-0.78
sembly
-0.75
ablishment
-0.75
Flavoring
-0.74
Seym
-0.73
udic
-0.73
sidx
-0.72
vironment
-0.71
quo
-0.70
laus
-0.69
POSITIVE LOGITS
ham
0.92
Motor
0.91
shire
0.86
ragon
0.81
clad
0.80
Mustang
0.80
bies
0.74
Ford
0.74
Ford
0.73
whe
0.71
Activations Density 0.009%