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

    Neuronpedia

    INDEX
    Explanations

    mentions of weekends

    oai_token-act-pair · gpt-3.5-turbo

    references to weekends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abet
    -0.85
    rates
    -0.77
    eded
    -0.75
    text
    -0.72
    idas
    -0.72
    ophers
    -0.71
    ris
    -0.70
    pres
    -0.70
    rate
    -0.69
    ifice
    -0.68
    POSITIVE LOGITS
     weekend
    1.27
     mornings
    1.18
     weekends
    1.14
     nights
    1.12
     afternoon
    1.11
     evenings
    1.01
     evening
    0.98
     Weekend
    0.98
     morning
    0.96
     brunch
    0.93
    Act Density 0.011%

    No Known Activations