INDEX
    Explanations

    references to the Mortal Kombat franchise and its related media

    New Auto-Interp
    Negative Logits
    <bos>
    -2.80
    -1.12
    /**
    -0.97
    /*
    -0.90
    
    
    -0.90
    @[+][
    -0.85
    <?
    -0.84
     springfox
    -0.78
    SequentialGroup
    -0.77
    #
    -0.75
    POSITIVE LOGITS
     increa
    2.04
     emphat
    2.03
     accla
    2.01
     affor
    1.94
     pessi
    1.90
     inev
    1.89
     maneu
    1.89
     indestru
    1.84
     impra
    1.84
     reluct
    1.78
    Act Density 0.316%

    No Known Activations