INDEX
Explanations
references to countries and their relationships or conditions
New Auto-Interp
Negative Logits
bourg
-0.16
alous
-0.15
ãĥŃãĥ³
-0.14
alink
-0.14
peq
-0.14
rganization
-0.14
lÃŃ
-0.13
emma
-0.13
اساÙĨ
-0.13
poons
-0.13
POSITIVE LOGITS
Cour
0.17
wide
0.16
á
0.15
Ober
0.15
imal
0.14
Cour
0.14
\Active
0.13
whose
0.13
osc
0.13
-wide
0.13
Activations Density 0.029%