INDEX
    Explanations

    relationships to feelings of belonging and alienation

    New Auto-Interp
    Negative Logits
    NamedQueries
    -0.58
    openConnection
    -0.50
     egyszer
    -0.48
     depolar
    -0.47
     peniten
    -0.46
    Toponymie
    -0.45
     fede
    -0.45
    stdc
    -0.44
     faiths
    -0.44
    featureID
    -0.44
    POSITIVE LOGITS
    SourceChecksum
    0.87
    Fits
    0.73
     incongru
    0.72
     fitting
    0.71
     esternos
    0.69
    fitting
    0.68
     Fits
    0.67
     fits
    0.67
    Fitting
    0.65
     bienvenue
    0.64
    Act Density 0.288%

    No Known Activations