INDEX
    Explanations

    the digit zero, with some sensitivity to closing parentheses and some document boundaries

    New Auto-Interp
    Negative Logits
     Wojciech
    -0.84
    WithIOException
    -0.82
    Manbalar
    -0.77
    wiſe
    -0.77
     Houſe
    -0.73
     AssemblyCulture
    -0.72
    mobileqq
    -0.72
    ẫy
    -0.71
    İŞ
    -0.71
    ſelves
    -0.71
    POSITIVE LOGITS
    /
    0.70
     Sab
    0.61
    est
    0.56
    en
    0.54
     Murdock
    0.54
    lan
    0.53
    nloa
    0.53
    kPa
    0.52
    mässig
    0.51
    ViewInit
    0.51
    Act Density 0.000%

    No Known Activations