INDEX
Explanations
names and surnames of individuals
New Auto-Interp
Negative Logits
ameda
-0.16
ubar
-0.15
znik
-0.15
uffs
-0.15
rias
-0.14
wr
-0.14
ä½ľèĢħ
-0.14
loc
-0.14
counterparts
-0.14
esy
-0.14
POSITIVE LOGITS
ich
0.24
иÑĩа
0.24
ski
0.22
iç
0.22
sky
0.21
ICH
0.20
itch
0.19
icz
0.19
na
0.18
skin
0.17
Activations Density 0.014%