INDEX
Explanations
references to groups or movements with strong devotion or followers
references to cults or cult-like groups
New Auto-Interp
Negative Logits
deen
-0.73
cknowled
-0.67
Turk
-0.65
forth
-0.65
lled
-0.63
lag
-0.61
Ness
-0.61
~~~~~~~~~~~~~~~~
-0.60
horn
-0.59
ordan
-0.58
POSITIVE LOGITS
ivating
1.13
ivated
1.06
ivation
1.06
urally
1.04
cult
0.96
etically
0.94
millenn
0.93
ophon
0.93
ists
0.92
etic
0.91
Activations Density 0.018%