INDEX
Explanations
patterns related to demographic statistics and beliefs
New Auto-Interp
Negative Logits
erg
-0.18
Ness
-0.14
erge
-0.14
Ferguson
-0.14
sie
-0.14
_Address
-0.14
art
-0.13
ERG
-0.13
οÏħλ
-0.13
viso
-0.13
POSITIVE LOGITS
enschaft
0.16
ãĥ¼ãĥķ
0.16
CTYPE
0.15
vrier
0.15
-types
0.15
\Mapping
0.15
ateur
0.14
ainen
0.14
Wizard
0.14
emoc
0.14
Activations Density 0.009%