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

    Neuronpedia

    INDEX
    Explanations

    captions from images

    oai_token-act-pair · gpt-3.5-turbo

    mentions of images or visuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sic
    -0.79
    die
    -0.75
    laws
    -0.74
    sed
    -0.71
    halla
    -0.71
    nesia
    -0.70
    Ļ½
    -0.70
    ky
    -0.70
    acies
    -0.69
    ulhu
    -0.69
    POSITIVE LOGITS
     caption
    1.46
     Gallery
    0.94
     Images
    0.90
     Album
    0.84
     gallery
    0.82
     Annotations
    0.81
     IMAGES
    0.80
     Image
    0.80
     Collection
    0.79
     galleries
    0.78
    Act Density 0.008%

    No Known Activations