INDEX
Explanations
geographical references or locations
New Auto-Interp
Negative Logits
berger
-0.15
over
-0.15
Bever
-0.14
enie
-0.14
spos
-0.14
alice
-0.14
NSS
-0.14
دÙĩÙħ
-0.14
ook
-0.14
Breitbart
-0.13
POSITIVE LOGITS
ikon
0.18
strap
0.15
center
0.15
provincial
0.15
Centre
0.14
961
0.14
closet
0.14
ulia
0.14
Ñĸдом
0.14
Center
0.14
Activations Density 0.015%