INDEX
Explanations
names and surnames related to family lineage
New Auto-Interp
Negative Logits
auc
-0.18
alo
-0.16
ião
-0.15
enti
-0.15
strict
-0.15
olland
-0.14
ichten
-0.14
rium
-0.14
thá»§
-0.14
ayer
-0.13
POSITIVE LOGITS
((__
0.16
craw
0.15
Mori
0.14
наÑĤÑĥ
0.14
Emin
0.13
_rsp
0.13
ERRU
0.13
ìĺ¥
0.13
दर
0.13
utow
0.13
Activations Density 0.013%