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

    Neuronpedia

    INDEX
    Explanations

    reported data or information from sources

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "by" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asy
    -0.76
    ivia
    -0.72
    itto
    -0.70
    ppa
    -0.68
    apest
    -0.68
     "$:/
    -0.67
    igrate
    -0.67
    inea
    -0.66
    ati
    -0.66
    chrome
    -0.66
    POSITIVE LOGITS
     virtue
    1.26
    laws
    1.09
    products
    0.99
     fiat
    0.86
     statute
    0.83
    product
    0.80
    gone
    0.76
     decree
    0.74
    catch
    0.72
     multiplying
    0.72
    Act Density 0.292%

    No Known Activations