INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Fotos
    -0.16
     Photos
    -0.15
    Photos
    -0.15
     photographs
    -0.14
    Fotos
    -0.14
    photos
    -0.14
     pictures
    -0.13
     fotografías
    -0.13
    Pictures
    -0.13
    /photos
    -0.13
    POSITIVE LOGITS
     image
    0.41
    image
    0.34
    	image
    0.34
    .image
    0.33
    (image
    0.32
    _image
    0.31
    'image
    0.30
    ’image
    0.30
    -image
    0.28
    Image
    0.27
    Act Density 0.034%

    No Known Activations