INDEX
    Explanations

    quotation mark

    New Auto-Interp
    Negative Logits
    .kill
    -0.08
     fathers
    -0.08
    ilsen
    -0.08
     Lyme
    -0.08
     bepaalt
    -0.08
    keet
    -0.08
     zaposlen
    -0.08
     jire
    -0.07
     nimet
    -0.07
    -0.07
    POSITIVE LOGITS
    FK
    0.08
    ½
    0.07
     bet
    0.07
    0.07
    ifel
    0.07
    _fk
    0.07
     prompts
    0.07
     drawings
    0.07
     thinker
    0.07
     condenser
    0.07
    Act Density 0.003%

    No Known Activations