INDEX
Explanations
references to Germany and German culture
New Auto-Interp
Negative Logits
GetInstance
-0.15
avic
-0.15
openhagen
-0.15
rimp
-0.14
792
-0.14
grese
-0.13
leground
-0.13
uluk
-0.13
Erotik
-0.13
ional
-0.13
POSITIVE LOGITS
orest
0.17
-speaking
0.16
andy
0.16
ersen
0.15
unch
0.15
.EntityManager
0.14
ufact
0.14
.contentType
0.14
dorf
0.14
fan
0.14
Activations Density 0.030%