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

    Neuronpedia

    INDEX
    Explanations

    references to software programming modules

    oai_token-act-pair · gpt-3.5-turbo

    references to specific software modules and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    photo
    -0.80
    isconsin
    -0.72
    ews
    -0.72
    creen
    -0.69
    tin
    -0.67
    furt
    -0.66
    bow
    -0.64
    nee
    -0.64
    IELD
    -0.64
    tale
    -0.63
    POSITIVE LOGITS
     loader
    0.90
    ules
    0.86
    mers
    0.83
     bund
    0.83
     modules
    0.80
    isters
    0.74
    urations
    0.72
    modules
    0.71
    matically
    0.71
    agn
    0.69
    Act Density 0.037%

    No Known Activations