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

    Neuronpedia

    INDEX
    Explanations

    dates and numbers mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the 21st century

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneous
    -0.87
     externalToEVAOnly
    -0.86
    ensional
    -0.78
    atics
    -0.75
    ochemical
    -0.74
    aped
    -0.71
    outed
    -0.71
    riages
    -0.71
    aneously
    -0.70
    apers
    -0.69
    POSITIVE LOGITS
    st
    1.27
    nect
    0.75
    istries
    0.73
    naire
    0.71
    ĪĴ
    0.71
    es
    0.70
    ĨĴ
    0.70
    âģ
    0.70
    WI
    0.70
    eous
    0.69
    Act Density 0.059%

    No Known Activations