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

    Neuronpedia

    INDEX
    Explanations

    file references within text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of file references or documentation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orical
    -0.76
    ĵĺ
    -0.75
    osate
    -0.75
    utra
    -0.73
    orically
    -0.72
    ische
    -0.71
    anson
    -0.69
    angular
    -0.69
    »Ĵ
    -0.69
    atform
    -0.68
    POSITIVE LOGITS
    thumbnails
    0.85
    Upload
    0.84
    20439
    0.80
    handle
    0.79
    ette
    0.75
    ystem
    0.73
     descriptor
    0.73
    backs
    0.71
     cabinets
    0.71
    mma
    0.70
    Act Density 0.022%

    No Known Activations