INDEX
    Explanations

    LaTeX code referencing equation labels with scaling

    New Auto-Interp
    Negative Logits
    ↵↵
    -1.70
    -1.03
    <bos>
    -0.94
    <eos>
    -0.91
      
    -0.89
    ↵↵↵
    -0.87
     The
    -0.83
    -0.82
    -0.81
     “
    -0.77
    POSITIVE LOGITS
     BnF
    0.80
    end
    0.77
     CWE
    0.75
     Himo
    0.71
     Coder
    0.69
     NSP
    0.67
     Paglinawan
    0.66
     NDL
    0.65
     ENO
    0.64
     Minion
    0.64
    Act Density 4.090%

    No Known Activations