INDEX
Explanations
mentions of various entities or groups, potentially related to entertainment or sports
names or titles of entities, particularly in entertainment or notable references
New Auto-Interp
Negative Logits
srfAttach
-0.73
exception
-0.68
ASED
-0.68
exemptions
-0.67
carbohyd
-0.67
dissemination
-0.64
Delivery
-0.62
suspensions
-0.62
ABLE
-0.61
ש
-0.61
POSITIVE LOGITS
mith
1.64
aurus
1.51
hift
1.42
ilver
1.41
peed
1.34
chool
1.33
cale
1.30
layer
1.29
hip
1.26
kaya
1.25
Activations Density 0.322%