INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    VIAF
    -0.77
    Geplaatst
    -0.65
     שוליים
    -0.59
     Roskov
    -0.57
     Veil
    -0.57
    LError
    -0.57
    XmlIgnore
    -0.56
    EClass
    -0.55
    portál
    -0.55
     mule
    -0.54
    POSITIVE LOGITS
    bootstrapcdn
    0.70
     Correction
    0.50
     rég
    0.50
    gulama
    0.48
     correction
    0.47
     Combined
    0.47
    Correction
    0.47
     retain
    0.46
    <bos>
    0.45
     rispet
    0.45
    Act Density 0.001%

    No Known Activations