INDEX
    Explanations

    names of notable individuals, particularly those named George

    New Auto-Interp
    Negative Logits
    uga
    -0.15
    inka
    -0.14
    763
    -0.14
    bjerg
    -0.14
    tier
    -0.13
    .INSTANCE
    -0.13
    agara
    -0.13
     bull
    -0.13
     mmap
    -0.13
     Rhodes
    -0.13
    POSITIVE LOGITS
     George
    0.17
    George
    0.16
    ackbar
    0.16
    readcr
    0.16
    idak
    0.15
    Ñİк
    0.15
    _NT
    0.15
    atetime
    0.14
    izzard
    0.14
    AVA
    0.14
    Act Density 0.031%

    No Known Activations