INDEX
Explanations
possessive pronouns referring to ownership or belonging
New Auto-Interp
Negative Logits
itud
-0.83
Æ
-0.69
vati
-0.67
Originally
-0.67
ĸļ
-0.67
ipal
-0.66
vous
-0.66
perse
-0.65
Appears
-0.65
YR
-0.64
POSITIVE LOGITS
favorite
1.24
favourite
1.15
own
1.06
fingertips
1.00
imagination
0.92
inbox
0.90
mileage
0.88
backyard
0.87
browsing
0.85
browser
0.85
Activations Density 0.090%