INDEX
Explanations
family members such as grandparents and grandchildren
references to grandmothers and grandfathers
New Auto-Interp
Negative Logits
ylon
-0.76
tics
-0.74
ologne
-0.69
rd
-0.68
acus
-0.68
ijk
-0.68
usal
-0.68
axis
-0.66
jab
-0.66
lez
-0.65
POSITIVE LOGITS
grandma
0.85
grandmother
0.85
father
0.84
Takeru
0.82
parents
0.80
grandfather
0.80
grandparents
0.78
aunt
0.78
Cherokee
0.76
mother
0.73
Activations Density 0.024%