INDEX
Explanations
references to World War II
New Auto-Interp
Negative Logits
snipp
-0.81
Wiz
-0.79
ciating
-0.76
Choice
-0.72
erd
-0.70
Vox
-0.70
BOOK
-0.70
POLITICO
-0.69
Word
-0.69
Thumbnails
-0.67
POSITIVE LOGITS
era
0.96
Veterans
0.91
vets
0.85
Memorial
0.82
veterans
0.82
Veteran
0.81
Era
0.78
veteran
0.77
Aviation
0.76
vet
0.76
Activations Density 0.047%