INDEX
Explanations
countries and their related aspects
mentions of nationalities, political affiliations, and cultural or societal identities
New Auto-Interp
Negative Logits
Canaver
-0.70
anwhile
-0.67
uador
-0.64
]'
-0.64
Guan
-0.62
aples
-0.59
hovah
-0.58
guiActiveUnfocused
-0.58
Rohing
-0.57
GOODMAN
-0.57
POSITIVE LOGITS
counterparts
1.15
counterpart
0.98
brethren
0.91
cousins
0.86
buddies
0.84
selves
0.82
holdings
0.82
cousin
0.79
arsenal
0.78
ancestors
0.78
Activations Density 0.743%