INDEX
Explanations
elements related to biographical and geographical information
New Auto-Interp
Negative Logits
itals
-0.18
logs
-0.16
deo
-0.15
Basket
-0.15
legs
-0.14
nore
-0.14
alten
-0.14
legg
-0.14
dzi
-0.14
.photos
-0.14
POSITIVE LOGITS
ÃŃa
0.44
ÃŃas
0.32
ija
0.31
иÑı
0.30
ie
0.29
ria
0.24
ία
0.24
ÑĸÑı
0.23
ÑĸÑĹ
0.21
ia
0.21
Activations Density 0.041%