INDEX
Explanations
references to the automotive company "Ford"
references to the Ford automobile brand
New Auto-Interp
Negative Logits
hemat
-0.70
laus
-0.68
ablishment
-0.67
quo
-0.65
vironment
-0.65
Sakuya
-0.64
huh
-0.64
Flavoring
-0.64
practitioner
-0.63
udic
-0.63
POSITIVE LOGITS
ham
0.96
Motor
0.93
shire
0.89
ragon
0.86
clad
0.86
Mustang
0.83
bies
0.82
Fiesta
0.77
erick
0.74
rera
0.70
Activations Density 0.019%