INDEX
Explanations
mentions of personal experiences and interactions related to family and friends
Possessive pronouns followed by family relations
my family and friends
New Auto-Interp
Negative Logits
出版年
-0.84
ViewFeatures
-0.74
Personendaten
-0.68
tableFuture
-0.66
InputDecoration
-0.66
таратура
-0.66
+#+#
-0.65
ujednoznacz
-0.65
Ведь
-0.65
محفوظة
-0.64
POSITIVE LOGITS
my
0.74
college
0.72
niece
0.67
granddaughter
0.66
nieces
0.66
daughters
0.65
daughter
0.64
coworker
0.64
grandsons
0.63
coworkers
0.63
Activations Density 0.419%