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

    Neuronpedia

    INDEX
    Explanations

    dates indicating a specific point in time or day of the week

    oai_token-act-pair · gpt-3.5-turbo

    references to time indicators and timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apons
    -0.68
    eps
    -0.61
    atche
    -0.58
    ãĢı
    -0.58
    apon
    -0.58
     cav
    -0.57
    Fish
    -0.57
    ersen
    -0.57
     Cop
    -0.57
    cart
    -0.55
    POSITIVE LOGITS
    liest
    0.65
     referral
    0.62
    outube
    0.61
     Pastebin
    0.61
    reports
    0.61
     Inquis
    0.61
    âĸĪ
    0.60
    arest
    0.60
     Unsure
    0.60
    URRENT
    0.59
    Act Density 0.083%

    No Known Activations