INDEX
Explanations
phrases indicating quantities or conditions related to actions
New Auto-Interp
Negative Logits
itſelf
-0.93
houſe
-0.89
cauſe
-0.82
ſhe
-0.82
ſche
-0.79
djangoproject
-0.77
Chriftian
-0.75
becauſe
-0.75
Bewußt
-0.75
Diſ
-0.74
POSITIVE LOGITS
the
0.84
a
0.83
an
0.78
,:),
0.73
writerow
0.73
)]=
0.72
mit
0.71
GEBURTSDATUM
0.70
haal
0.70
Literatur
0.70
Activations Density 0.002%