INDEX
    Explanations

    references to prominent individuals or personalities in media and music

    New Auto-Interp
    Negative Logits
    ipa
    -0.15
    asInstanceOf
    -0.14
     vill
    -0.14
    udios
    -0.14
     nod
    -0.14
    bast
    -0.13
     Kramer
    -0.13
     Ulus
    -0.13
    hel
    -0.13
     reap
    -0.13
    POSITIVE LOGITS
    bach
    0.17
    arus
    0.15
    еÑĩно
    0.15
     Omni
    0.14
     Byron
    0.14
    ensus
    0.14
     Buy
    0.14
     Dixon
    0.14
    edit
    0.14
    dorf
    0.14
    Act Density 0.221%

    No Known Activations