INDEX
Explanations
personal pronouns 'I' and 'my' used in context with another person
instances of the pronoun "I."
New Auto-Interp
Negative Logits
Vald
-0.73
tains
-0.69
imum
-0.66
-0.65
Net
-0.64
rules
-0.63
Torrent
-0.58
iP
-0.58
Ezekiel
-0.57
Applications
-0.56
POSITIVE LOGITS
'm
1.22
've
1.18
'll
1.05
suppose
0.97
ggy
0.91
verson
0.91
guess
0.91
RL
0.89
'd
0.88
ANA
0.85
Activations Density 0.098%