INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    @yahoo
    -0.17
    ull
    -0.16
    andom
    -0.15
    ocht
    -0.15
    @hotmail
    -0.14
    isky
    -0.14
     ActionTypes
    -0.14
    otron
    -0.14
    ister
    -0.13
    bull
    -0.13
    POSITIVE LOGITS
    .qual
    0.15
    744
    0.14
    www
    0.14
    owo
    0.14
    -ignore
    0.14
     fas
    0.14
    -www
    0.14
    hdl
    0.14
     www
    0.14
    iras
    0.13
    Act Density 0.053%

    No Known Activations