INDEX
    Explanations

    visual and descriptive concepts

    New Auto-Interp
    Negative Logits
    0.46
    राबरी
    0.46
    avings
    0.44
    0.44
    ರ್
    0.44
     Giappone
    0.44
     curated
    0.44
     едино
    0.43
     பட்
    0.43
     curate
    0.43
    POSITIVE LOGITS
    Graphical
    0.45
    Temperature
    0.42
     Darkness
    0.41
    Signing
    0.40
    Painting
    0.39
     vivid
    0.39
    综合
    0.38
     pictorial
    0.38
    Texture
    0.38
     portrayal
    0.38
    Act Density 0.012%

    No Known Activations