INDEX
Explanations
mentions of historical figures involved in political or military contexts
New Auto-Interp
Negative Logits
pinulongan
-0.69
RectangleBorder
-0.64
OGND
-0.62
gangen
-0.61
NamedQueries
-0.60
_
-0.59
".
-0.59
avelmente
-0.58
Monfieur
-0.58
Eſ
-0.56
POSITIVE LOGITS
kasarigan
0.66
conmigo
0.61
moveToFirst
0.56
unitOfWork
0.51
Билгалдахарш
0.48
printStackTrace
0.48
us
0.48
referenties
0.47
الرياضيه
0.47
@[+][
0.46
Activations Density 0.946%