Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to images with captions in a text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Image" and its associated numerical values and copyright information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.93
    unts
    -0.88
    lies
    -0.79
    sole
    -0.76
    unin
    -0.74
    laws
    -0.74
    uum
    -0.70
    ugs
    -0.70
    aptic
    -0.70
    uckle
    -0.70
    POSITIVE LOGITS
    Image
    1.17
    Images
    1.12
     Image
    1.08
     Images
    1.04
    gallery
    1.04
     Thumbnails
    1.01
     caption
    0.96
    Photo
    0.89
     Gallery
    0.86
    MAP
    0.83
    Act Density 0.016%

    No Known Activations