INDEX
    Explanations

    references to the name "Margaret" and its variations

    New Auto-Interp
    Negative Logits
    etin
    -0.17
    essler
    -0.16
    eon
    -0.16
    erman
    -0.15
    _ASSUME
    -0.15
    erase
    -0.14
    eti
    -0.14
    FontAwesome
    -0.14
    oog
    -0.14
    TextChanged
    -0.14
    POSITIVE LOGITS
    ta
    0.24
    te
    0.20
    tes
    0.20
    ten
    0.18
    tings
    0.17
    table
    0.17
    tery
    0.17
    ting
    0.16
    ted
    0.16
     Thatcher
    0.15
    Act Density 0.005%

    No Known Activations