INDEX
Explanations
demographic information related to study participants
New Auto-Interp
Negative Logits
ßerdem
-0.43
qvarna
-0.39
verbeter
-0.38
improvement
-0.38
ismet
-0.38
ersdorf
-0.36
Verbesserung
-0.34
umme
-0.34
EnableWeb
-0.34
GENERAL
-0.34
POSITIVE LOGITS
female
0.86
male
0.81
male
0.75
female
0.74
females
0.72
Female
0.68
Male
0.66
disambiguazione
0.66
Female
0.66
Male
0.64
Activations Density 0.708%