INDEX
Explanations
references to spouses and marital relationships
New Auto-Interp
Negative Logits
ü
-0.72
dio
-0.61
'''
-0.59
continuity
-0.58
seq
-0.58
im
-0.57
er
-0.55
oc
-0.55
UCL
-0.54
alai
-0.54
POSITIVE LOGITS
husband
2.17
Husband
2.04
husbands
1.88
husband
1.88
Husband
1.86
hubby
1.63
wife
1.58
marito
1.53
esposo
1.41
Wife
1.39
Activations Density 0.048%