INDEX
    Explanations

    the end of parenthetical phrases

    New Auto-Interp
    Negative Logits
    Dziękuję
    -0.81
     purpoſe
    -0.73
    ^(@)
    -0.73
     Hieronymus
    -0.72
     pleaſure
    -0.69
     himſelf
    -0.69
     myſelf
    -0.69
     itſelf
    -0.68
     Monfieur
    -0.68
    GIH
    -0.67
    POSITIVE LOGITS
    :✨
    0.71
    man
    0.66
    Man
    0.66
     Man
    0.64
    +#+
    0.63
    0.63
    m
    0.58
    0.56
     الرياضيه
    0.56
     man
    0.55
    Act Density 0.000%

    No Known Activations