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

    Neuronpedia

    INDEX
    Explanations

    references to specific time periods or lengths of time

    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
    riad
    -0.90
    ramid
    -0.89
    otle
    -0.86
    illard
    -0.82
    dinand
    -0.80
    unin
    -0.77
    iasis
    -0.74
    tical
    -0.74
    inatory
    -0.71
    artisan
    -0.71
    POSITIVE LOGITS
     duration
    1.01
    Duration
    0.98
    duration
    0.92
     periods
    0.91
     elapsed
    0.86
     dur
    0.83
     lapse
    0.82
     ÏĦ
    0.80
     intervals
    0.78
    frames
    0.77
    Act Density 0.029%

    No Known Activations