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

    Neuronpedia

    INDEX
    Explanations

    timestamps or durations of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of duration or continuation of events or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.78
    iasco
    -0.73
    omical
    -0.70
    axter
    -0.68
    ippy
    -0.67
    artisan
    -0.67
    ault
    -0.66
    ulkan
    -0.66
    ilan
    -0.66
    ongyang
    -0.65
    POSITIVE LOGITS
    gs
    0.84
    running
    0.83
     rampant
    0.82
    swick
    0.79
    escape
    0.78
    estones
    0.77
     benches
    0.76
    around
    0.75
    ners
    0.73
    runners
    0.72
    Act Density 0.041%

    No Known Activations