INDEX
Explanations
references to spirituality and religion
New Auto-Interp
Negative Logits
copg
-0.58
Normdatei
-0.57
PRNewswire
-0.55
ufficient
-0.55
aDecoder
-0.54
сылкі
-0.53
nolia
-0.51
ای
-0.50
❸
-0.50
labus
-0.49
POSITIVE LOGITS
s
3.87
ی
1.64
ся
1.59
ы
1.41
ים
1.39
ship
1.25
schen
1.24
scape
1.18
sı
1.18
ات
1.17
Activations Density 2.707%