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

    Neuronpedia

    INDEX
    Explanations

    time-related words and phrases, particularly durations such as "years" and "days."

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of time spent on activities or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icator
    -0.68
    amount
    -0.67
    icist
    -0.64
    erity
    -0.62
    zsche
    -0.61
    ãĥ¤
    -0.59
    Ľ
    -0.59
     Cutter
    -0.59
    named
    -0.58
     cf
    -0.58
    POSITIVE LOGITS
     studying
    0.97
     researching
    0.93
     outdoors
    0.89
     cultivating
    0.89
     preparing
    0.88
     photograp
    0.87
     immersed
    0.86
     analyzing
    0.84
     exploring
    0.84
     exposing
    0.84
    Act Density 0.104%

    No Known Activations