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

    Neuronpedia

    INDEX
    Explanations

    mentions of privacy or private settings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "private."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.83
    è¦ļéĨĴ
    -0.79
    orsi
    -0.77
    addons
    -0.76
    DAY
    -0.76
    xual
    -0.72
    OPA
    -0.72
    Dispatch
    -0.71
    OE
    -0.69
    ocalypse
    -0.69
    POSITIVE LOGITS
     sector
    0.96
     equity
    0.96
     affairs
    0.78
    sector
    0.74
    mouth
    0.73
     private
    0.72
     rented
    0.71
     opinion
    0.70
     investigator
    0.69
     minded
    0.69
    Act Density 0.018%

    No Known Activations