INDEX
Explanations
instances of email addresses or login information in the text
New Auto-Interp
Negative Logits
otty
-0.17
anzi
-0.15
irie
-0.15
alat
-0.14
eny
-0.14
опол
-0.14
adox
-0.14
kie
-0.14
yn
-0.13
buster
-0.13
POSITIVE LOGITS
ajas
0.16
Roe
0.15
acc
0.15
Quint
0.14
icari
0.14
Sant
0.14
acas
0.14
Cand
0.14
.getBean
0.14
veis
0.14
Activations Density 0.006%