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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "duration" is mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of duration in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.90
    riad
    -0.88
    otle
    -0.85
    illard
    -0.83
    iasis
    -0.77
    dinand
    -0.77
    bold
    -0.71
    artisan
    -0.71
    unin
    -0.69
    ebus
    -0.69
    POSITIVE LOGITS
     duration
    1.04
    Duration
    0.97
    duration
    0.93
     elapsed
    0.84
     periods
    0.83
    etheless
    0.80
     lapse
    0.78
     ÏĦ
    0.78
     lasting
    0.77
     intervals
    0.76
    Act Density 0.017%

    No Known Activations