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

    Neuronpedia

    INDEX
    Explanations

    dates and time durations

    oai_token-act-pair · gpt-3.5-turbo

    references to time, specifically focusing on the concept of "last" as in preceding periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cil
    -0.70
    kaya
    -0.68
    /#
    -0.68
    rend
    -0.63
     Franch
    -0.62
    aunders
    -0.62
    stadt
    -0.62
    mbuds
    -0.61
    aband
    -0.61
    keyes
    -0.61
    POSITIVE LOGITS
     gasp
    0.97
     week
    0.94
     month
    0.93
     ditch
    0.92
     year
    0.91
     decade
    0.88
    ebin
    0.86
     night
    0.83
     Gleaming
    0.83
     rites
    0.79
    Act Density 0.075%

    No Known Activations