INDEX
Explanations
references to Western regions or cultures
New Auto-Interp
Negative Logits
iseite
-0.78
źdz
-0.72
มาะ
-0.71
rubles
-0.71
Recife
-0.68
ofür
-0.66
makeConstraints
-0.66
NOPQRST
-0.65
zocht
-0.65
onaut
-0.64
POSITIVE LOGITS
Western
1.96
Western
1.88
WESTERN
1.79
western
1.72
WESTERN
1.70
western
1.69
Eastern
1.42
Eastern
1.32
Northwestern
1.29
northwestern
1.25
Activations Density 0.049%