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

    Neuronpedia

    INDEX
    Explanations

    image credits or captions

    oai_token-act-pair · gpt-3.5-turbo

    visual content such as images and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lies
    -0.85
    merce
    -0.77
    unin
    -0.76
    sole
    -0.74
    laws
    -0.73
    tml
    -0.72
    gger
    -0.72
    dies
    -0.70
    unts
    -0.70
    cair
    -0.69
    POSITIVE LOGITS
     caption
    1.07
     Images
    1.01
    Image
    1.00
     Image
    0.99
     Gallery
    0.99
     Thumbnails
    0.93
    Images
    0.92
     IMAGES
    0.89
     Comics
    0.85
     Courtesy
    0.82
    Act Density 0.018%

    No Known Activations