INDEX
    Explanations

    quotes or direct speech in the text

    New Auto-Interp
    Negative Logits
    Obrigada
    -0.67
    ERÍA
    -0.57
    ÁRIO
    -0.56
    ícone
    -0.55
    IFORNIA
    -0.55
    edal
    -0.55
     oxid
    -0.54
    homonymie
    -0.53
    CCESS
    -0.53
     guard
    -0.52
    POSITIVE LOGITS
    "
    1.71
    1.70
    ")
    1.43
    ",
    1.41
    ”,
    1.33
    1.31
    ”)
    1.28
    ".
    1.23
    )"
    1.23
    ,"
    1.23
    Act Density 0.138%

    No Known Activations