INDEX
    Explanations

    statements about infidelity and its moral implications

    New Auto-Interp
    Negative Logits
    gui
    -0.16
    anus
    -0.15
    _TD
    -0.14
    apur
    -0.14
    urovision
    -0.14
    /DD
    -0.14
    á»§
    -0.14
    anson
    -0.14
    ushima
    -0.14
    ÄĻki
    -0.13
    POSITIVE LOGITS
    548
    0.17
    akin
    0.16
     fat
    0.16
    isz
    0.15
    ÏĪη
    0.15
     bilm
    0.15
     //!<
    0.14
    ÑĤÑĢа
    0.14
    stown
    0.14
    549
    0.14
    Act Density 0.150%

    No Known Activations