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

    Neuronpedia

    INDEX
    Explanations

    dates mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to dates or temporal information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ui
    -0.67
    ought
    -0.66
    essen
    -0.61
    adia
    -0.60
    oso
    -0.60
    addons
    -0.59
    ibur
    -0.59
    lets
    -0.57
    asca
    -0.56
    among
    -0.56
    POSITIVE LOGITS
     date
    4.10
    date
    3.00
     dates
    2.97
     Date
    2.63
     Dates
    2.33
    Date
    2.33
    dates
    1.79
     dated
    1.73
    dated
    1.63
     dating
    1.51
    Act Density 0.015%

    No Known Activations