INDEX
Explanations
names and surnames of individuals
New Auto-Interp
Negative Logits
.lp
-0.15
bbing
-0.14
avad
-0.14
centered
-0.14
oulder
-0.14
concentrated
-0.13
iju
-0.13
Pur
-0.13
à¹ĩà¸Ķ
-0.13
alm
-0.13
POSITIVE LOGITS
ãĥ»
0.20
Contributor
0.19
·
0.18
âĹĭ
0.18
olle
0.18
|
0.18
기ìŀIJ
0.17
âĢ¢
0.17
CONTRIBUT
0.17
Uncategorized
0.17
Activations Density 0.082%