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

    Neuronpedia

    INDEX
    Explanations

    time-related terms like days, weeks, or years

    oai_token-act-pair · gpt-3.5-turbo

    terms related to time periods and their recurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elvet
    -0.72
    ierrez
    -0.70
    emort
    -0.69
    CHQ
    -0.65
    Dat
    -0.65
     Gleaming
    -0.65
     classmate
    -0.64
    placed
    -0.63
    ntil
    -0.62
    ogle
    -0.62
    POSITIVE LOGITS
    osphere
    0.74
     festivities
    0.73
     ahead
    0.71
    liest
    0.71
     finale
    0.70
     schedule
    0.69
    worms
    0.68
    iverse
    0.67
    finals
    0.67
    urst
    0.67
    Act Density 0.089%

    No Known Activations