INDEX
Explanations
references to gums and oral health topics
New Auto-Interp
Negative Logits
ogo
-0.17
Bra
-0.15
raith
-0.14
peare
-0.14
TextLabel
-0.14
anga
-0.14
enta
-0.14
ough
-0.14
itel
-0.14
ogh
-0.14
POSITIVE LOGITS
uen
0.15
arest
0.15
illez
0.14
soever
0.14
onde
0.14
loquent
0.14
Ùijد
0.14
åīĽ
0.14
idd
0.14
figcaption
0.14
Activations Density 0.006%