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

    Neuronpedia

    INDEX
    Explanations

    references to specific online platforms, specifically GitHub

    oai_token-act-pair · gpt-3.5-turbo

    mentions of GitHub

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vati
    -0.77
    ecause
    -0.75
    \":
    -0.73
    undai
    -0.71
    igslist
    -0.71
    ises
    -0.70
    respond
    -0.70
    eal
    -0.70
    phal
    -0.69
     destro
    -0.67
    POSITIVE LOGITS
     repository
    0.99
     Pages
    0.98
     repositories
    0.92
     repo
    0.81
     Commons
    0.79
     Mellon
    0.79
     Contribut
    0.75
     GitHub
    0.73
     snipp
    0.72
     Username
    0.71
    Act Density 0.006%

    No Known Activations