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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, specifically phrases indicating "this" or "last" week or month

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.72
    ensitive
    -0.68
     knots
    -0.60
    velt
    -0.60
    anded
    -0.59
    oidal
    -0.59
    apego
    -0.57
    izontal
    -0.56
    Trend
    -0.56
    arte
    -0.55
    POSITIVE LOGITS
     weekend
    1.22
     afternoon
    1.21
     week
    1.18
     evening
    1.12
     morning
    1.10
     month
    1.02
     night
    0.95
     mornings
    0.92
     summer
    0.91
     evenings
    0.88
    Act Density 0.146%

    No Known Activations