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

    Neuronpedia

    INDEX
    Explanations

    image captions

    oai_token-act-pair · gpt-3.5-turbo

    instances of images or visual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.85
    unts
    -0.84
     heel
    -0.76
    lies
    -0.73
     convers
    -0.73
    sole
    -0.72
    ggles
    -0.71
    manship
    -0.70
    laws
    -0.70
    rieg
    -0.70
    POSITIVE LOGITS
    Image
    1.30
     Image
    1.18
    Images
    1.13
    gallery
    1.11
     Thumbnails
    1.06
     Images
    1.05
     PHOTO
    0.89
    Picture
    0.89
    Photo
    0.87
     Gallery
    0.86
    Act Density 0.013%

    No Known Activations