INDEX
Explanations
personal possessive pronouns followed by verbs
possessive pronouns, particularly "my."
New Auto-Interp
Negative Logits
itect
-0.88
apiece
-0.83
ciation
-0.73
Uriel
-0.72
illac
-0.69
arians
-0.69
respectively
-0.69
aphael
-0.64
etz
-0.64
yourselves
-0.64
POSITIVE LOGITS
own
1.33
anmar
1.26
stery
1.12
wife
1.10
opic
1.10
grandmother
1.10
dad
1.09
opia
1.08
ocard
1.06
husband
1.06
Activations Density 0.141%