INDEX
Explanations
references to the sea or ocean
New Auto-Interp
Negative Logits
pude
-0.32
head
-0.29
job
-0.29
Peters
-0.26
Ein
-0.26
Haut
-0.26
druk
-0.25
Hend
-0.25
Henderson
-0.25
Four
-0.25
POSITIVE LOGITS
gull
0.69
gulls
0.68
Geplaatst
0.66
CommonModule
0.65
faring
0.64
ویکیپدیا
0.63
expandindo
0.63
utafitiHapana
0.62
Hauptartikel
0.61
存于互联网档案馆
0.61
Activations Density 0.153%