INDEX
Explanations
references to family dynamics and social relations
New Auto-Interp
Negative Logits
GEBURTSDATUM
-0.58
fédé
-0.48
scribers
-0.47
nôtre
-0.46
ours
-0.46
diren
-0.46
GEBURTS
-0.45
cadre
-0.44
cadres
-0.44
particip
-0.44
POSITIVE LOGITS
Chwiliwch
0.58
ValueStyle
0.49
ScopeManager
0.47
ViewFeatures
0.47
IsContent
0.45
fuck
0.44
fucking
0.41
himself
0.41
tagHelperRunner
0.40
FUCKING
0.39
Activations Density 0.289%