INDEX
    Explanations

    references to cinematic or media franchises

    New Auto-Interp
    Negative Logits
    elog
    -0.17
    hpp
    -0.16
    _PATCH
    -0.16
    STRU
    -0.16
    ово
    -0.15
    peria
    -0.14
    onom
    -0.14
    .createComponent
    -0.14
    Mess
    -0.14
    brit
    -0.14
    POSITIVE LOGITS
     figures
    0.36
     figure
    0.34
    -figure
    0.32
     Figures
    0.29
     figura
    0.28
    figures
    0.28
     fig
    0.26
     repaint
    0.25
    figure
    0.24
     artic
    0.24
    Act Density 0.018%

    No Known Activations