INDEX
Explanations
references to the Vietnam War
references to the Vietnam War and related terms
New Auto-Interp
Negative Logits
*/(
-1.10
heet
-0.82
lev
-0.80
tered
-0.80
essional
-0.79
rencies
-0.72
imov
-0.72
idges
-0.72
âĸ¬âĸ¬
-0.68
tical
-0.68
POSITIVE LOGITS
Nguyen
1.07
vet
0.86
oleon
0.82
ogue
0.82
War
0.80
Veterans
0.78
vets
0.77
Nam
0.77
Laos
0.76
Vietnamese
0.75
Activations Density 0.023%