INDEX
Explanations
names of individuals who have passed away
language related to death and loss
New Auto-Interp
Negative Logits
lag
-0.70
fantasy
-0.69
precon
-0.69
antasy
-0.68
linear
-0.67
Myth
-0.67
atters
-0.66
consensus
-0.66
Configuration
-0.65
Random
-0.65
POSITIVE LOGITS
indicted
0.94
rieving
0.92
deceased
0.89
sentenced
0.87
arra
0.85
relatives
0.84
arnaev
0.83
nephew
0.82
slain
0.81
icts
0.80
Activations Density 0.549%