INDEX
Explanations
references to youth and young people
New Auto-Interp
Negative Logits
hausen
-0.17
inge
-0.15
DataMember
-0.15
lej
-0.15
onth
-0.15
urette
-0.15
entin
-0.15
ISE
-0.15
ibur
-0.15
æŃ¢
-0.14
POSITIVE LOGITS
paren
0.14
Rai
0.14
à¥ģब
0.14
dif
0.14
ersen
0.14
.ht
0.13
eea
0.13
Ric
0.13
Bolt
0.13
inks
0.13
Activations Density 0.014%