INDEX
Explanations
past tense verbs and auxiliary verbs indicating actions or conditions
New Auto-Interp
Negative Logits
574
-0.17
ichi
-0.15
ogle
-0.15
aves
-0.15
ibern
-0.15
-heading
-0.15
802
-0.14
.aw
-0.14
ighth
-0.14
312
-0.14
POSITIVE LOGITS
_:*
0.15
/pub
0.15
arry
0.14
åħ¼
0.14
ctal
0.14
Kı
0.14
throp
0.14
ssi
0.14
zet
0.14
soc
0.13
Activations Density 0.388%