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 academic journals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chuk
    -0.66
    ucha
    -0.64
    rises
    -0.63
    ranged
    -0.63
     cust
    -0.61
    ACY
    -0.61
    baugh
    -0.60
     Glover
    -0.60
    isin
    -0.60
    cream
    -0.60
    POSITIVE LOGITS
     journal
    1.13
    ournals
    1.02
     journals
    0.99
    Journal
    0.92
     Journals
    0.91
     papers
    0.91
    Paper
    0.89
    ļéĨĴ
    0.85
    lishing
    0.81
    etta
    0.81
    Act Density 0.011%

    No Known Activations