INDEX
Explanations
words and phrases indicating effort, teamwork, and accomplishments
New Auto-Interp
Negative Logits
razier
-0.17
Bald
-0.15
xd
-0.14
ormsg
-0.14
oldem
-0.14
oppers
-0.14
kav
-0.14
iko
-0.14
unsch
-0.14
ELLOW
-0.13
POSITIVE LOGITS
eld
0.18
producing
0.17
/GPL
0.17
linger
0.17
produce
0.17
creating
0.17
tae
0.16
#create
0.15
creation
0.15
Creating
0.15
Activations Density 0.004%