INDEX
Explanations
references to personal pronouns and possessive adjectives
personal pronouns or references like "My", "I", and "wife".
New Auto-Interp
Negative Logits
itſelf
-0.59
tilbud
-0.56
ſelf
-0.54
ſted
-0.54
plads
-0.54
forbin
-0.48
canst
-0.48
strøm
-0.47
vigilance
-0.47
getHeight
-0.47
POSITIVE LOGITS
my
0.71
My
0.66
I
0.66
me
0.66
My
0.62
my
0.60
MY
0.60
getMy
0.59
myfile
0.59
estekak
0.54
Activations Density 0.113%