INDEX
    Explanations

    occurrences of the phrase "my name is" and variations of introductions

    New Auto-Interp
    Negative Logits
    одо
    -0.17
    abit
    -0.15
    립
    -0.14
    ÄĽl
    -0.14
    peror
    -0.14
    ijken
    -0.14
    arend
    -0.14
    auer
    -0.14
    esp
    -0.14
    нам
    -0.14
    POSITIVE LOGITS
    ifu
    0.15
     Jaune
    0.14
    clerosis
    0.14
    åı«
    0.14
     withheld
    0.14
    urgeon
    0.14
    isposable
    0.13
    меÑĤ
    0.13
    _digest
    0.13
    /Area
    0.13
    Act Density 0.017%

    No Known Activations