INDEX
Explanations
phrases related to possession or ownership
possessive pronouns
New Auto-Interp
Negative Logits
noon
-0.74
ablishment
-0.73
Pwr
-0.71
yang
-0.67
Unsure
-0.67
haus
-0.66
vell
-0.65
dding
-0.65
nown
-0.64
Chall
-0.63
POSITIVE LOGITS
own
1.81
entire
1.17
self
1.04
OWN
1.04
rightful
1.02
selves
0.99
destiny
0.99
fingerprints
0.97
grandmother
0.97
daughter
0.97
Activations Density 0.356%