INDEX
Explanations
references to blood in various contexts
New Auto-Interp
Negative Logits
Administrativna
-0.62
contentLoaded
-0.59
NSCoder
-0.59
Personensuche
-0.58
vuestros
-0.57
propOrder
-0.56
mármol
-0.56
zijne
-0.55
Stimme
-0.55
endpush
-0.54
POSITIVE LOGITS
blood
0.91
Blood
0.81
Blood
0.65
outdoor
0.62
Outdoor
0.61
blood
0.60
hormone
0.58
BLOOD
0.57
entre
0.55
Se
0.53
Activations Density 0.400%