INDEX
    Explanations

    violence and death

    New Auto-Interp
    Negative Logits
    leave
    -0.07
    operators
    -0.07
    当然
    -0.07
    ths
    -0.07
     womens
    -0.07
     faux
    -0.06
    ่าท
    -0.06
     nerd
    -0.06
    -0.06
    -0.06
    POSITIVE LOGITS
    .MustCompile
    0.06
     Connor
    0.06
     운동
    0.06
    ,,,,,,,,
    0.06
     Daemon
    0.06
     toolbox
    0.06
     Conor
    0.06
    	process
    0.05
    mailbox
    0.05
    .vector
    0.05
    Act Density 0.021%

    No Known Activations