INDEX
Explanations
references to the country "Burundi"
references to a specific entity or subject
New Auto-Interp
Negative Logits
uncture
-0.83
selves
-0.67
dfx
-0.64
éĹĺ
-0.62
+#
-0.62
esthetic
-0.62
naires
-0.60
anwhile
-0.60
DonaldTrump
-0.60
xual
-0.59
POSITIVE LOGITS
querque
1.22
rows
1.11
rito
1.03
geoning
1.00
leigh
0.96
rill
0.96
ger
0.95
ley
0.93
row
0.92
rowing
0.92
Activations Density 0.008%