INDEX
Explanations
mentions of family relationships and personal history
possessive pronouns related to family and personal relationships
New Auto-Interp
Negative Logits
ãĥĦ
-0.79
ãĥķãĤ¡
-0.78
guiActiveUn
-0.75
AMS
-0.75
Ops
-0.73
ĸļ
-0.73
available
-0.73
aber
-0.72
女
-0.70
Downloadha
-0.69
POSITIVE LOGITS
father
1.98
dad
1.98
parents
1.91
mother
1.90
grandmother
1.84
mom
1.82
grandfather
1.79
grandparents
1.74
aunt
1.71
Dad
1.65
Activations Density 0.171%