INDEX
Explanations
references to online forms and personal information fields
New Auto-Interp
Negative Logits
idon
-0.16
iamond
-0.16
okol
-0.15
abei
-0.15
agh
-0.15
NEG
-0.14
Naming
-0.14
Notice
-0.14
ÏĦεÏĤ
-0.14
Duy
-0.14
POSITIVE LOGITS
목
0.17
0.17
age
0.16
birth
0.15
phone
0.15
0.15
0.15
telephone
0.15
job
0.14
desired
0.14
Activations Density 0.041%