INDEX
    Explanations

    references to personal names and their familial connections

    New Auto-Interp
    Negative Logits
     tvb
    -0.14
    онÑĮ
    -0.14
    rieg
    -0.14
     Deutsch
    -0.14
    arshal
    -0.14
     celib
    -0.14
    lez
    -0.13
    ìľ
    -0.13
    и
    -0.13
     ÐĴоз
    -0.13
    POSITIVE LOGITS
    inox
    0.17
    umann
    0.16
    MG
    0.15
    ertools
    0.15
    604
    0.14
    üstü
    0.14
    uzzi
    0.14
    CHAT
    0.14
    241
    0.14
    mlink
    0.14
    Act Density 0.009%

    No Known Activations