INDEX
Explanations
references to artistic genres or forms related to music and film
New Auto-Interp
Negative Logits
ybrid
-0.17
erotiske
-0.16
o
-0.15
áš
-0.15
Ñij
-0.15
Scho
-0.14
kä
-0.14
AsString
-0.14
etc
-0.14
knull
-0.14
POSITIVE LOGITS
sz
0.21
egy
0.21
agy
0.20
Cs
0.19
akat
0.18
harm
0.18
szer
0.17
hiba
0.17
rias
0.17
Sz
0.16
Activations Density 0.010%