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

    Neuronpedia

    INDEX
    Explanations

    topics related to government, health, and sports

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to social issues and public affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RESULTS
    -0.58
    DATA
    -0.54
    >[
    -0.50
    })
    -0.46
    ipher
    -0.46
    ocratic
    -0.46
    fml
    -0.46
    )."
    -0.46
    SOURCE
    -0.45
    xious
    -0.45
    POSITIVE LOGITS
    lance
    0.51
     --------------------
    0.51
     âĵĺ
    0.49
    ues
    0.48
    ="#
    0.48
    allery
    0.47
    antes
    0.47
    uese
    0.46
     auctions
    0.45
    iage
    0.45
    Act Density 4.661%

    No Known Activations