INDEX
Explanations
possessive pronouns indicating ownership
possessive pronouns that indicate ownership or relationships
New Auto-Interp
Negative Logits
rupal
-0.73
haus
-0.68
WARD
-0.66
nown
-0.66
arthed
-0.66
actic
-0.65
pract
-0.65
ciation
-0.63
代
-0.62
Tip
-0.61
POSITIVE LOGITS
own
1.51
self
1.45
selves
1.41
grandchildren
1.28
daughters
1.18
wife
1.17
parents
1.16
grandmother
1.15
brother
1.14
OWN
1.14
Activations Density 0.276%