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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions, particularly focusing on durations such as years, months, and centuries

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of time, particularly years and months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.65
    alg
    -0.65
     subp
    -0.64
    kef
    -0.64
    inite
    -0.64
    Ka
    -0.62
    odes
    -0.61
    Haw
    -0.61
     Amph
    -0.59
     Cron
    -0.58
    POSITIVE LOGITS
     ago
    1.17
     elapsed
    0.86
     apiece
    0.85
     Ago
    0.83
     gestation
    0.74
     worth
    0.69
    姫
    0.66
    long
    0.66
    iosity
    0.66
     silence
    0.65
    Act Density 0.128%

    No Known Activations