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

    images and their associated captions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dies
    -0.86
    halla
    -0.79
    merce
    -0.72
    laws
    -0.72
    tons
    -0.72
    »Ĵ
    -0.71
    die
    -0.69
    anders
    -0.69
    ueless
    -0.69
    achus
    -0.68
    POSITIVE LOGITS
     caption
    1.38
     copyright
    1.21
     Gallery
    0.95
     gallery
    0.94
     Courtesy
    0.93
    Image
    0.93
     Image
    0.89
     Images
    0.87
     Source
    0.86
     Comics
    0.85
    Act Density 0.016%

    No Known Activations