INDEX
Explanations
personal possessive pronouns like 'my' and 'I'
pronouns, particularly "I" and "my," reflecting personal perspective in the text
New Auto-Interp
Negative Logits
nesota
-0.70
endar
-0.66
aults
-0.65
lihood
-0.64
itton
-0.63
cemic
-0.62
neapolis
-0.60
rencies
-0.60
lectic
-0.60
ouston
-0.59
POSITIVE LOGITS
bara
0.83
Promise
0.70
ona
0.68
udic
0.67
'm
0.67
apolis
0.67
aning
0.65
recommend
0.64
gladly
0.63
Cats
0.63
Activations Density 0.284%