INDEX
    Explanations

    phrases and words indicative of requests or inquiries

    New Auto-Interp
    Negative Logits
    /pkg
    -0.19
     thick
    -0.15
    idUser
    -0.14
    adol
    -0.14
    odb
    -0.14
     Thick
    -0.14
    ahren
    -0.14
     Gecko
    -0.14
     turist
    -0.14
     Lust
    -0.13
    POSITIVE LOGITS
    ISION
    0.16
    iesen
    0.16
    wel
    0.16
    .visual
    0.14
    olet
    0.14
    eous
    0.14
    mlink
    0.14
    owski
    0.14
    iates
    0.14
     Archer
    0.14
    Act Density 0.030%

    No Known Activations