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

    Neuronpedia

    INDEX
    Explanations

    sentences that are part of a media caption

    oai_token-act-pair · gpt-3.5-turbo

    references to media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ranch
    -0.79
    hap
    -0.77
    ivas
    -0.75
    quartered
    -0.71
    essee
    -0.70
    uca
    -0.69
    profits
    -0.65
    reek
    -0.64
     hindsight
    -0.63
     Gree
    -0.63
    POSITIVE LOGITS
     Thumbnails
    0.80
    Camera
    0.78
    "></
    0.76
    Container
    0.75
     caption
    0.73
    Support
    0.73
    Guard
    0.72
    Medical
    0.71
     Loading
    0.71
    View
    0.71
    Act Density 0.019%

    No Known Activations