INDEX
Explanations
references to "American" or "America" in various contexts
New Auto-Interp
Negative Logits
ibrill
-0.48
يتيمه
-0.46
routeProvider
-0.43
chuva
-0.43
ModelExpression
-0.41
+#+#
-0.41
tunik
-0.40
fianco
-0.39
giarism
-0.39
OGND
-0.38
POSITIVE LOGITS
American
2.97
Americans
2.78
American
2.69
America
2.67
american
2.50
AMERICAN
2.44
amer
2.38
Americans
2.38
America
2.36
american
2.31
Activations Density 0.214%