INDEX
    Explanations

    references to specific religious texts and their historical context

    New Auto-Interp
    Negative Logits
    COUVER
    -0.69
     kasarigan
    -0.68
    ufnahme
    -0.65
     Visconti
    -0.63
    LEncoder
    -0.63
    xase
    -0.61
    SPJ
    -0.61
    tsburgh
    -0.60
    Koko
    -0.60
    bbene
    -0.59
    POSITIVE LOGITS
     Israel
    0.92
    Israel
    0.91
     Israeli
    0.90
     Israël
    0.88
     israel
    0.83
    Israeli
    0.82
     Jacob
    0.81
    israel
    0.80
    Jacob
    0.80
     Hebrew
    0.79
    Act Density 2.448%

    No Known Activations