INDEX
    Explanations

    mentions of people's names and their associated activities or achievements

    New Auto-Interp
    Negative Logits
    imei
    -0.16
    ercul
    -0.15
    aphore
    -0.15
     confirm
    -0.15
    ismu
    -0.14
     MQ
    -0.14
    .rf
    -0.14
    oser
    -0.14
    mq
    -0.14
     confirmed
    -0.14
    POSITIVE LOGITS
     yat
    0.16
     WHATSOEVER
    0.16
    TRS
    0.15
    _CM
    0.15
     folding
    0.14
    ÑĢедиÑĤ
    0.14
    blas
    0.14
    ussen
    0.14
     صاÙĦØŃ
    0.14
    bet
    0.13
    Act Density 0.433%

    No Known Activations