INDEX
Explanations
mentions of the word "sons"
references to the word "sons" and denote family relationships
New Auto-Interp
Negative Logits
de
-0.68
ebin
-0.67
pmwiki
-0.67
AU
-0.67
constitu
-0.65
ANN
-0.64
EVA
-0.63
Rail
-0.62
ALLY
-0.62
patient
-0.62
POSITIVE LOGITS
sons
1.11
hip
1.04
daughters
0.93
doms
0.91
lings
0.89
ieve
0.88
pins
0.88
ongs
0.87
manship
0.86
terday
0.84
Activations Density 0.009%