INDEX
    Explanations

    references to specific individuals, particularly those named Megan or Randy

    New Auto-Interp
    Negative Logits
     '').
    -0.47
     "");
    
    -0.45
    ||}
    -0.44
    fiore
    -0.41
    //////////////
    -0.41
     fl
    -0.39
     Fru
    -0.39
    '..
    -0.38
    ''.
    -0.38
    tableFuture
    -0.37
    POSITIVE LOGITS
     Megan
    2.14
    Megan
    2.11
     Meghan
    0.96
    Meghan
    0.89
     ainfi
    0.83
     Meg
    0.80
    Meg
    0.79
     megane
    0.79
     mauva
    0.77
     enfans
    0.75
    Act Density 0.001%

    No Known Activations