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

    Neuronpedia

    INDEX
    Explanations

    references to specific units of time, such as "days" or "weeks"

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, specifically "days" and "weeks"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geh
    -0.63
     Type
    -0.61
     Entered
    -0.61
    iving
    -0.60
    inav
    -0.60
     DI
    -0.59
     Option
    -0.58
    amus
    -0.57
     Neph
    -0.57
    ISO
    -0.56
    POSITIVE LOGITS
    pring
    1.05
    imester
    0.80
    hops
    0.80
    days
    0.78
    hift
    0.77
    steen
    0.76
     weeks
    0.76
     afternoon
    0.74
    ²¾
    0.74
     mornings
    0.72
    Act Density 0.066%

    No Known Activations