INDEX
Explanations
phrases indicating birthdates or birth information
New Auto-Interp
Negative Logits
ewis
-0.17
_
-0.17
ab
-0.16
oints
-0.15
oler
-0.15
oline
-0.15
yat
-0.15
ctor
-0.14
leads
-0.14
,
-0.14
POSITIVE LOGITS
iaux
0.16
ĵåIJį
0.16
_CRITICAL
0.15
IEnumerator
0.15
ÏĦÏģι
0.15
GOODMAN
0.14
.Blocks
0.14
ProcessEvent
0.14
Ú¯ÛĮ
0.14
ılıp
0.14
Activations Density 0.020%