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

    Neuronpedia

    INDEX
    Explanations

    images or photos in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to image captions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.90
    laws
    -0.86
    etheless
    -0.84
    ighter
    -0.79
    uckle
    -0.78
    unts
    -0.77
    unin
    -0.76
    manship
    -0.74
    rieg
    -0.74
    bye
    -0.74
    POSITIVE LOGITS
     caption
    1.08
     Image
    1.04
     Gallery
    0.93
     Collection
    0.88
    gallery
    0.86
     Album
    0.86
     Comics
    0.85
     Images
    0.84
     Collections
    0.84
     Thumbnails
    0.83
    Act Density 0.014%

    No Known Activations