INDEX
Explanations
references to father figures and paternal relationships
New Auto-Interp
Negative Logits
uilla
-0.62
illaries
-0.59
ylen
-0.59
__))
-0.59
الحره
-0.58
Jovi
-0.58
delu
-0.57
Vidite
-0.57
verket
-0.57
EDEFAULT
-0.56
POSITIVE LOGITS
Fathers
1.40
fathers
1.38
FATHER
1.26
father
1.23
Father
1.18
Father
1.08
father
1.06
fathers
1.06
Père
1.04
père
0.98
Activations Density 0.039%