INDEX
Explanations
references to geographical locations or entities associated with history
New Auto-Interp
Negative Logits
colo
-0.16
ouv
-0.15
bourg
-0.15
chied
-0.14
chal
-0.14
é¢
-0.13
eced
-0.13
punt
-0.13
çļ
-0.13
imp
-0.13
POSITIVE LOGITS
(en
0.15
oser
0.14
otel
0.14
wie
0.14
596
0.14
Aquarium
0.14
NB
0.14
ovich
0.14
sympath
0.14
.en
0.14
Activations Density 0.018%