INDEX
Explanations
expressions of affection and interest in personal or creative pursuits
New Auto-Interp
Negative Logits
asje
-0.17
orian
-0.16
æ¢
-0.15
елиÑĩ
-0.15
iyi
-0.15
ouri
-0.15
agen
-0.14
uyu
-0.14
you
-0.14
anje
-0.14
POSITIVE LOGITS
me
0.19
isel
0.17
dale
0.16
uire
0.16
UGIN
0.16
Champ
0.15
eland
0.15
dela
0.15
ede
0.14
me
0.14
Activations Density 0.147%