INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     bunlar
    -0.07
     začí
    -0.07
    isoft
    -0.07
     แพ
    -0.06
     truyền
    -0.06
    378
    -0.06
    _NAV
    -0.06
    ';
    ↵
    ↵
    -0.06
    />.↵↵
    -0.06
     Carlos
    -0.06
    POSITIVE LOGITS
     razor
    0.07
     appliance
    0.07
    um
    0.07
     ;)
    0.06
    -loving
    0.06
     Portal
    0.06
    Rendering
    0.06
    gi
    0.06
    .std
    0.06
    0.06
    Act Density 0.001%

    No Known Activations