INDEX
    Explanations

    elements related to image metadata and descriptions

    New Auto-Interp
    Negative Logits
     images
    -0.21
     logo
    -0.18
    images
    -0.18
     pictures
    -0.18
     photographs
    -0.18
     Bilder
    -0.18
     Images
    -0.18
    -images
    -0.17
     imagery
    -0.17
     Logo
    -0.17
    POSITIVE LOGITS
     crops
    0.21
     caption
    0.21
     Caption
    0.20
     crop
    0.19
    crop
    0.18
     quality
    0.18
    _caption
    0.18
     captions
    0.18
     Quality
    0.18
    caption
    0.18
    Act Density 0.053%

    No Known Activations