INDEX
Explanations
references to the term "ban" and its variations, particularly in relation to music and cultural contexts
New Auto-Interp
Negative Logits
aÄŁ
-0.16
klass
-0.15
strict
-0.15
lesia
-0.15
elig
-0.15
onte
-0.14
ibt
-0.14
aeda
-0.14
Strict
-0.14
wards
-0.14
POSITIVE LOGITS
offee
0.27
ishment
0.26
ished
0.26
quets
0.26
ishing
0.25
ister
0.21
ISTER
0.20
anas
0.20
eful
0.20
ruptcy
0.20
Activations Density 0.017%