INDEX
Explanations
proper nouns related to locations and names
New Auto-Interp
Negative Logits
alse
-0.07
reff
-0.07
hari
-0.07
cek
-0.07
edl
-0.07
áln
-0.07
ocos
-0.07
umer
-0.06
erti
-0.06
.nano
-0.06
POSITIVE LOGITS
resident
0.12
native
0.12
-based
0.09
-native
0.08
resident
0.08
native
0.08
-born
0.08
natives
0.08
born
0.08
residents
0.07
Activations Density 0.018%