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

    Neuronpedia

    INDEX
    Explanations

    book titles with the word "by" in them

    oai_token-act-pair · gpt-3.5-turbo

    attributions in the form of "by" followed by an author's name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     retard
    -0.73
    ETF
    -0.71
    inary
    -0.69
    bia
    -0.68
    SPONSORED
    -0.67
    asy
    -0.67
    inea
    -0.66
    upon
    -0.66
    ginx
    -0.65
    imately
    -0.65
    POSITIVE LOGITS
     virtue
    1.11
    products
    0.88
    product
    0.86
    akuya
    0.81
    gone
    0.81
    laws
    0.79
     default
    0.73
    pass
    0.72
     extension
    0.71
     omission
    0.70
    Act Density 0.123%

    No Known Activations