INDEX
Explanations
possessive pronouns and possessive forms indicating ownership
New Auto-Interp
Negative Logits
@(
-0.15
uteur
-0.14
ones
-0.14
oneself
-0.14
//{{-0.14
aal
-0.13
oger
-0.13
živ
-0.13
å·Ŀ
-0.13
ppers
-0.13
POSITIVE LOGITS
goal
0.30
aim
0.30
only
0.30
focus
0.22
goal
0.22
job
0.22
’e
0.21
biggest
0.20
greatest
0.20
task
0.20
Activations Density 0.379%