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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of days, months, and years within a document

    oai_token-act-pair · gpt-3.5-turbo

    temporal references regarding years and days

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     packaging
    -0.65
     Unch
    -0.65
    ufact
    -0.61
     recy
    -0.58
    UTF
    -0.57
    apons
    -0.57
     ple
    -0.56
    onite
    -0.55
    ĨĴ
    -0.55
    alth
    -0.55
    POSITIVE LOGITS
    endment
    0.77
    shire
    0.69
     Amendments
    0.63
    sol
    0.63
     Outlook
    0.62
    )--
    0.60
    stroke
    0.59
     GMT
    0.59
     thereafter
    0.59
    ,.
    0.58
    Act Density 0.425%

    No Known Activations