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

    Neuronpedia

    INDEX
    Explanations

    references to specific time periods in history or geological time scales

    oai_token-act-pair · gpt-3.5-turbo

    references to large numbers and time periods in millions or billions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    robe
    -0.67
    iquid
    -0.67
    krit
    -0.65
    puter
    -0.64
    allo
    -0.63
    chart
    -0.62
    respect
    -0.60
    enegger
    -0.59
    ibaba
    -0.57
    ****************
    -0.57
    POSITIVE LOGITS
     years
    1.51
    years
    1.37
     Years
    1.21
     BCE
    1.11
    Years
    1.08
    yrs
    1.07
     kilometers
    1.05
     kilometres
    1.04
    year
    1.04
     miles
    1.01
    Act Density 0.059%

    No Known Activations