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

    Neuronpedia

    INDEX
    Explanations

    average values or statistics related to different categories such as wages, prices, life expectancy, and more

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to average measurements and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¦ãĤ¹
    -0.84
    atography
    -0.80
    lez
    -0.77
    Ü
    -0.76
    andro
    -0.76
    ãĤ¤ãĥĪ
    -0.75
    selves
    -0.75
    pecially
    -0.75
    afort
    -0.75
    leaders
    -0.71
    POSITIVE LOGITS
     lifespan
    1.10
     hourly
    1.03
     weekday
    1.02
     annual
    0.98
     yearly
    0.98
     jo
    0.97
     weekly
    0.93
     age
    0.92
     duration
    0.90
     fastball
    0.90
    Act Density 0.057%

    No Known Activations