INDEX
    Explanations

    references to figures and figurines

    New Auto-Interp
    Negative Logits
     sortBy
    -0.73
    vidia
    -0.66
    phazard
    -0.65
    Eddy
    -0.64
     ddelweddau
    -0.63
    raszam
    -0.62
     Eddy
    -0.59
     Friedhof
    -0.58
     nameof
    -0.58
     médaille
    -0.58
    POSITIVE LOGITS
     figures
    1.34
     figure
    1.30
    figure
    1.28
     Figures
    1.22
     FIGURES
    1.13
    figures
    1.13
     Figure
    1.13
    Figure
    1.12
    Figures
    1.08
     figured
    0.93
    Act Density 0.019%

    No Known Activations