INDEX
    Explanations

    Pagans and related concepts

    mentions of paganism or related terms

    New Auto-Interp
    Negative Logits
    ingly
    -0.79
    wards
    -0.73
    cream
    -0.71
    stroke
    -0.69
     Commodore
    -0.69
     Kelvin
    -0.68
    lessly
    -0.65
    hirt
    -0.65
    hold
    -0.64
    pick
    -0.63
    POSITIVE LOGITS
    asus
    1.02
    agate
    0.99
    asa
    0.97
    agraph
    0.93
    onent
    0.89
    osa
    0.87
    ahon
    0.86
    oda
    0.85
    olin
    0.84
    issance
    0.83
    Act Density 0.032%

    No Known Activations