INDEX
    Explanations

    monetary values or financial figures

    New Auto-Interp
    Negative Logits
    aepernick
    -0.14
    951
    -0.14
    chem
    -0.14
    .wikipedia
    -0.14
    üf
    -0.14
    901
    -0.14
    _excerpt
    -0.14
    alls
    -0.14
    úsqueda
    -0.14
    xon
    -0.13
    POSITIVE LOGITS
    ajor
    0.15
     Mi
    0.14
    anford
    0.13
    ETA
    0.13
    inho
    0.13
       
    0.13
    ecz
    0.13
    airy
    0.13
     Mod
    0.12
    ÃŃna
    0.12
    Act Density 0.140%

    No Known Activations