INDEX
    Explanations

    references to promotional materials and marketing content

    New Auto-Interp
    Negative Logits
    olumn
    -0.18
     Writers
    -0.17
    Writer
    -0.16
     Photograph
    -0.15
     writers
    -0.15
    adol
    -0.15
    ewriter
    -0.14
     novels
    -0.14
    writers
    -0.14
    (Photo
    -0.14
    POSITIVE LOGITS
     video
    0.59
     videos
    0.58
    video
    0.49
    -video
    0.48
    è§Ĩé¢ij
    0.46
     Videos
    0.46
    videos
    0.44
     Video
    0.44
     VIDEO
    0.44
    .video
    0.44
    Act Density 0.529%

    No Known Activations