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

    Neuronpedia

    INDEX
    Explanations

    references to time periods or durations, specifically when it involves a hundred years

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "century" or related time spans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liga
    -0.82
    agents
    -0.75
    vals
    -0.73
    ensity
    -0.71
    doms
    -0.69
    ancial
    -0.69
    appa
    -0.67
    ramid
    -0.66
    ym
    -0.66
    gur
    -0.65
    POSITIVE LOGITS
    ocene
    0.83
     Ago
    0.81
     Reincarn
    0.77
     ago
    0.76
     Antiqu
    0.72
    ĸļ
    0.71
     Sta
    0.69
     BCE
    0.69
    osaurs
    0.67
     millennia
    0.67
    Act Density 0.012%

    No Known Activations