INDEX
    Explanations

    terms related to images or visual content

    New Auto-Interp
    Negative Logits
    ázka
    -0.63
    glicher
    -0.60
    entlicher
    -0.59
    робка
    -0.58
     بيها
    -0.58
    PreferredItem
    -0.57
    izacja
    -0.57
    ικοί
    -0.57
    Obrázky
    -0.55
     eigener
    -0.54
    POSITIVE LOGITS
    지를
    0.87
     ואת
    0.82
    기를
    0.79
     را
    0.76
    리를
    0.74
    名を
    0.71
    車を
    0.69
     것을
    0.67
    ளை
    0.66
    者を
    0.66
    Act Density 0.116%

    No Known Activations