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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific journals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucha
    -0.71
    isin
    -0.65
    rises
    -0.65
    chuk
    -0.64
    ACY
    -0.64
    cream
    -0.62
    forced
    -0.62
     Afgh
    -0.59
     cust
    -0.59
     Liberties
    -0.59
    POSITIVE LOGITS
     journal
    1.21
     journals
    1.06
    ournals
    1.04
     papers
    0.94
     Journals
    0.91
    Journal
    0.82
    uing
    0.82
    Paper
    0.81
    ļéĨĴ
    0.81
     articles
    0.79
    Act Density 0.009%

    No Known Activations