INDEX
Explanations
verbs indicating change or transformation
New Auto-Interp
Negative Logits
Eck
-0.15
acco
-0.15
loth
-0.14
ahun
-0.14
isia
-0.14
ncia
-0.13
ali
-0.13
DAR
-0.13
xaa
-0.13
okol
-0.13
POSITIVE LOGITS
adic
0.16
erable
0.15
_WARN
0.15
uga
0.14
fra
0.14
obsc
0.14
226
0.14
çĩ
0.14
à¹Īาย
0.14
IllegalAccessException
0.14
Activations Density 0.143%