INDEX
Explanations
possessive pronouns followed by personal attributes/family
New Auto-Interp
Negative Logits
Husband
0.95
spouse
0.93
Spouse
0.92
Wife
0.90
husband
0.89
husband
0.88
esposo
0.86
wife
0.86
সন্তানদের
0.84
spouse
0.83
POSITIVE LOGITS
parents
0.84
ouders
0.80
genitori
0.78
родителей
0.78
grandfather
0.76
والدین
0.75
родители
0.74
grandmother
0.72
classmates
0.71
fathers
0.70
Activations Density 0.018%