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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time duration or schedules

    oai_token-act-pair · gpt-3.5-turbo

    references to continuous time periods, particularly related to hours

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.79
     Galile
    -0.74
    esan
    -0.69
    dinand
    -0.69
    chance
    -0.66
    ften
    -0.65
    rect
    -0.64
     Augustus
    -0.61
    smanship
    -0.61
    088
    -0.60
    POSITIVE LOGITS
    endment
    1.11
    mith
    0.87
    glass
    0.78
    £ı
    0.76
    ï¸
    0.76
    etheless
    0.76
     outage
    0.74
     elapsed
    0.73
    urst
    0.70
    ftime
    0.69
    Act Density 0.025%

    No Known Activations