INDEX
Explanations
mentions of family relationships, particularly fathers and their roles
references to parental figures, particularly fathers and mothers
New Auto-Interp
Negative Logits
Flavoring
-0.79
andestine
-0.69
resso
-0.67
vernment
-0.66
ORGE
-0.65
ickr
-0.65
polling
-0.62
ANN
-0.61
ename
-0.59
jriwal
-0.59
POSITIVE LOGITS
hesis
1.12
heses
1.10
hetical
1.00
hetically
0.95
baugh
0.84
hood
0.81
load
0.78
stones
0.75
wife
0.73
father
0.72
Activations Density 0.067%