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

    Neuronpedia

    INDEX
    Explanations

    dates in the format "Month Day" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    dates, specifically occurrences in March

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cumbers
    -0.76
    kB
    -0.69
    folios
    -0.68
     unnecess
    -0.67
    lder
    -0.67
     cleansing
    -0.65
    gone
    -0.64
    udging
    -0.64
    itaire
    -0.63
     tox
    -0.62
    POSITIVE LOGITS
     Madness
    1.10
    riage
    0.90
    nard
    0.88
     2019
    0.85
    ing
    0.85
    flower
    0.85
    yard
    0.82
     2015
    0.81
     Arbor
    0.80
    steen
    0.79
    Act Density 0.021%

    No Known Activations