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

    Neuronpedia

    INDEX
    Explanations

    images with captions

    oai_token-act-pair · gpt-3.5-turbo

    references to images in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dies
    -0.79
    die
    -0.79
    gger
    -0.77
    lies
    -0.73
    laws
    -0.73
    ulhu
    -0.73
    merce
    -0.72
    uckle
    -0.71
    tml
    -0.71
    »Ĵ
    -0.71
    POSITIVE LOGITS
     caption
    1.08
    Image
    0.99
     Images
    0.96
     Image
    0.96
     Gallery
    0.90
     Album
    0.89
     Courtesy
    0.89
     IMAGES
    0.88
     copyright
    0.87
    Images
    0.87
    Act Density 0.023%

    No Known Activations