INDEX
Explanations
mentions of distinct cultural or ethnic groups
New Auto-Interp
Negative Logits
contentLoaded
-0.66
SequentialGroup
-0.63
IntoConstraints
-0.56
twimg
-0.51
Clarendon
-0.50
crose
-0.50
gouv
-0.48
ниця
-0.47
vrt
-0.47
propOrder
-0.47
POSITIVE LOGITS
tribes
0.69
hlander
0.68
tribe
0.65
0.63
race
0.62
tribus
0.61
peoples
0.60
nomadic
0.59
speaking
0.58
inhabiting
0.57
Activations Density 0.483%