INDEX
    Explanations

    numerical data or statistics

    New Auto-Interp
    Negative Logits
     All
    -1.16
    All
    -1.13
    all
    -0.98
    ALL
    -0.88
     all
    -0.86
     ALL
    -0.84
    オール
    -0.75
     Все
    -0.62
    -0.61
     все
    -0.61
    POSITIVE LOGITS
     video
    1.18
     Video
    1.12
    Video
    1.11
     vidéo
    1.10
    video
    1.08
     VIDEO
    0.98
     videos
    0.98
     видео
    0.96
     Videos
    0.94
     vídeo
    0.92
    Act Density 1.337%

    No Known Activations