INDEX
    Explanations

    references to movies and their associated cast members

    New Auto-Interp
    Negative Logits
    å¹
    -0.15
    ghost
    -0.15
    lsru
    -0.14
    ëł´
    -0.14
     кваÑĢ
    -0.14
    jist
    -0.13
     bomber
    -0.13
    _secret
    -0.13
    phant
    -0.13
    itesse
    -0.13
    POSITIVE LOGITS
     leather
    0.19
     rough
    0.18
     crude
    0.18
     Heavy
    0.17
    ç²Ĺ
    0.17
     highway
    0.17
     motorcycle
    0.17
    污
    0.16
     icon
    0.16
     violence
    0.16
    Act Density 0.424%

    No Known Activations