INDEX
    Explanations

    instances of the word "just."

    New Auto-Interp
    Negative Logits
    ceae
    -0.16
    morgan
    -0.16
    299
    -0.15
     Ramos
    -0.15
    ftware
    -0.15
    Readable
    -0.15
    faq
    -0.14
    /***/
    -0.14
    /umd
    -0.14
     Modal
    -0.14
    POSITIVE LOGITS
    ifi
    0.16
     takový
    0.16
    mann
    0.16
    IFI
    0.15
    vier
    0.14
    indo
    0.14
    otec
    0.14
     finished
    0.13
    AF
    0.13
    undos
    0.13
    Act Density 0.046%

    No Known Activations