INDEX
Explanations
the infinitive form of verbs, particularly those introducing actions or intentions
New Auto-Interp
Negative Logits
legen
-0.16
寸
-0.15
agra
-0.15
arts
-0.15
INY
-0.14
eton
-0.14
:animated
-0.14
Nga
-0.14
roc
-0.14
Ung
-0.14
POSITIVE LOGITS
umper
0.16
ingly
0.16
infect
0.16
chied
0.15
Birch
0.15
pres
0.14
opsy
0.14
(/[
0.13
ahoo
0.13
inf
0.13
Activations Density 0.025%