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

    Neuronpedia

    INDEX
    Explanations

    days of the week

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days of the week and weekends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jri
    -0.70
    rahim
    -0.67
    lda
    -0.66
    Reviewed
    -0.66
    eering
    -0.65
    emort
    -0.64
    dinand
    -0.62
    Memory
    -0.62
     Confeder
    -0.62
     Rousse
    -0.60
    POSITIVE LOGITS
    creen
    1.33
    days
    1.16
    hift
    1.09
    pring
    1.07
    cale
    0.99
    hips
    0.98
    ilver
    0.96
    chool
    0.95
    DAY
    0.94
    aturdays
    0.91
    Act Density 0.043%

    No Known Activations