INDEX
    Explanations

    references to specific films or cinematic works

    New Auto-Interp
    Negative Logits
    ÏģÏīν
    -0.16
    å͝
    -0.16
    dna
    -0.15
     Naked
    -0.15
    asley
    -0.15
    illon
    -0.14
    #ac
    -0.14
    FTA
    -0.14
    eson
    -0.14
    eken
    -0.14
    POSITIVE LOGITS
    ippo
    0.32
    thy
    0.30
    aments
    0.28
    mm
    0.28
    ipp
    0.26
    ming
    0.26
    mland
    0.25
    ament
    0.24
    ial
    0.24
    med
    0.23
    Act Density 0.008%

    No Known Activations