INDEX
Explanations
themes related to systemic issues of power, privilege, and social justice
New Auto-Interp
Negative Logits
GEBURTSDATUM
-0.83
RegressionTest
-0.68
principalTable
-0.68
featureID
-0.66
InvalidProtocol
-0.61
NameInMap
-0.61
beginnetje
-0.60
AssemblyCompany
-0.59
Autoritní
-0.58
lorette
-0.58
POSITIVE LOGITS
suggests
0.72
proves
0.66
suggest
0.61
reminds
0.60
seems
0.57
gives
0.56
illustrates
0.55
explains
0.55
assures
0.54
indicates
0.54
Activations Density 1.444%