INDEX
Explanations
mentions of people and their interactions or characteristics
New Auto-Interp
Negative Logits
enth
-0.15
gaard
-0.15
illos
-0.15
ivé
-0.15
avy
-0.15
erald
-0.15
isty
-0.14
aler
-0.14
ambio
-0.14
emoc
-0.14
POSITIVE LOGITS
tractor
0.16
665
0.16
OU
0.15
ext
0.15
SingleOrDefault
0.14
disturbed
0.13
ARC
0.13
ECTOR
0.13
NSS
0.13
uiten
0.13
Activations Density 0.080%