INDEX
    Explanations

    equality comparisons in code

    New Auto-Interp
    Negative Logits
    er
    -0.76
    Portail
    -0.76
    dür
    -0.71
     Viter
    -0.69
    rizio
    -0.67
     Rolf
    -0.66
    inburgh
    -0.64
    es
    -0.63
    [`
    -0.62
     Radu
    -0.60
    POSITIVE LOGITS
     ==
    1.63
    ]==
    1.21
    ================
    1.16
    ']==
    1.14
    ")==
    1.08
    )==
    1.08
    ==
    1.00
     !=
    0.96
    =============
    0.96
    rzost
    0.91
    Act Density 0.055%

    No Known Activations