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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is representing or advocating for a specific entity or idea

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate representation or speaking on behalf of someone or something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    6000
    -0.72
    é¾
    -0.67
    CLE
    -0.66
    LAB
    -0.62
    Math
    -0.62
    Ping
    -0.60
    Beg
    -0.60
    venants
    -0.60
    marine
    -0.60
    8000
    -0.60
    POSITIVE LOGITS
    gery
    1.08
    geries
    1.06
    bidden
    1.04
     instance
    0.85
     example
    0.80
     starters
    0.80
    vantage
    0.76
    gotten
    0.75
    olid
    0.71
     awhile
    0.68
    Act Density 0.192%

    No Known Activations