INDEX
    Explanations

    references to specific famous individuals or royal figures

    New Auto-Interp
    Negative Logits
     Signalez
    -0.56
    RenderAtEndOf
    -0.54
     становника
    -0.52
     master
    -0.51
    itmen
    -0.51
     Frisco
    -0.48
    tanooga
    -0.47
    :✨
    -0.47
     PROF
    -0.47
     Отечественной
    -0.46
    POSITIVE LOGITS
     démocr
    0.74
     titolata
    0.72
     présidenti
    0.71
     nucléaire
    0.70
     normaux
    0.69
     termica
    0.67
     hereditary
    0.66
     decorativos
    0.66
     avoient
    0.65
     PLWABN
    0.65
    Act Density 0.278%

    No Known Activations