INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    وعية
    -0.08
     nation
    -0.08
    Temporary
    -0.08
     Alleen
    -0.08
     Animated
    -0.07
     temporary
    -0.07
     ien
    -0.07
    WND
    -0.07
    pital
    -0.07
     Forrest
    -0.07
    POSITIVE LOGITS
    /pre
    0.08
    Ns
    0.08
    әк
    0.07
    elt
    0.07
    akar
    0.07
    orc
    0.07
     свою
    0.07
    atsi
    0.07
     svoju
    0.07
     či
    0.07
    Act Density 0.171%

    No Known Activations