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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases, specifically indicating when events are scheduled to happen

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating scheduled events or deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anon
    -0.77
    sav
    -0.67
    aps
    -0.65
    agate
    -0.62
     currents
    -0.62
    =-=-=-=-=-=-=-=-
    -0.62
     Tornado
    -0.62
    zee
    -0.61
     VIDEOS
    -0.61
     Column
    -0.61
    POSITIVE LOGITS
     diligence
    1.13
    lling
    0.95
    lled
    0.84
    endment
    0.72
     cancell
    0.70
    ratulations
    0.69
     overdue
    0.68
     releg
    0.68
    giving
    0.68
    ller
    0.67
    Act Density 0.018%

    No Known Activations