INDEX
    Explanations

    references to films and the film industry

    New Auto-Interp
    Negative Logits
    ODEV
    -0.15
    emy
    -0.15
    asma
    -0.15
     filler
    -0.15
    laus
    -0.14
    ed
    -0.14
    opl
    -0.14
    lage
    -0.14
    ities
    -0.14
     haut
    -0.14
    POSITIVE LOGITS
    /software
    0.16
     noir
    0.16
    urg
    0.15
    /video
    0.15
    presso
    0.15
    ERCHANT
    0.14
    arshal
    0.14
    strip
    0.14
    pear
    0.14
    obar
    0.13
    Act Density 0.053%

    No Known Activations