INDEX
Explanations
forms of the verb "play" and associated subjects or pronouns
New Auto-Interp
Negative Logits
ecies
-0.17
UDGE
-0.16
undo
-0.16
_unix
-0.16
nex
-0.15
nih
-0.15
driven
-0.15
ìĻ
-0.14
mmo
-0.14
axe
-0.14
POSITIVE LOGITS
akis
0.18
ipar
0.15
par
0.15
mans
0.15
ialis
0.15
Ruf
0.14
asil
0.14
-base
0.14
urch
0.14
De
0.14
Activations Density 0.025%