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

    Neuronpedia

    INDEX
    Explanations

    keywords related to technical instructions or steps

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "by."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qqa
    -0.85
    aroo
    -0.74
    SPONSORED
    -0.72
    gow
    -0.71
    ijah
    -0.69
    ppa
    -0.69
    south
    -0.68
    itled
    -0.67
    Silver
    -0.66
    atem
    -0.64
    POSITIVE LOGITS
     virtue
    1.20
    products
    1.11
     multiplying
    1.00
    laws
    0.86
     selecting
    0.83
     default
    0.83
     adding
    0.82
    product
    0.81
     applying
    0.81
     clicking
    0.80
    Act Density 0.153%

    No Known Activations