INDEX
    Explanations

    occurrences of the dash character

    New Auto-Interp
    Negative Logits
     seek
    -0.15
    ibli
    -0.14
    riba
    -0.14
    abar
    -0.14
    ague
    -0.14
    ÂŃt
    -0.14
    Pin
    -0.13
    alan
    -0.13
    gor
    -0.13
    zew
    -0.13
    POSITIVE LOGITS
    _exempt
    0.15
    esser
    0.15
    optera
    0.14
    fsp
    0.14
    iens
    0.14
    inand
    0.14
    erton
    0.14
    Subview
    0.14
    ENCE
    0.13
    _macros
    0.13
    Act Density 0.068%

    No Known Activations