INDEX
    Explanations

    phrases related to movie-going experiences and cinema culture

    New Auto-Interp
    Negative Logits
    225
    -0.17
     Grove
    -0.15
    ald
    -0.14
     Laboratories
    -0.14
     cheek
    -0.14
     Sez
    -0.14
    218
    -0.14
     exec
    -0.14
    arin
    -0.14
    289
    -0.14
    POSITIVE LOGITS
    ilos
    0.17
     Trails
    0.15
    itles
    0.15
    æĦıæĢĿ
    0.14
    eking
    0.14
    isko
    0.14
    dbcTemplate
    0.14
    attended
    0.14
    kiem
    0.14
    iginal
    0.13
    Act Density 0.107%

    No Known Activations