INDEX
Explanations
names of individuals associated with obituaries or memorials
New Auto-Interp
Negative Logits
opic
-0.17
odox
-0.14
viron
-0.14
ihanna
-0.14
RK
-0.14
ournée
-0.14
iei
-0.14
ollapse
-0.14
aeper
-0.14
sola
-0.13
POSITIVE LOGITS
Jr
0.91
III
0.77
Sr
0.71
II
0.65
jr
0.64
IV
0.62
III
0.59
Sr
0.52
jr
0.50
sr
0.49
Activations Density 0.192%