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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity, especially related to small amounts or the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etin
    -0.15
     style
    -0.14
    ellar
    -0.14
    endar
    -0.14
    JI
    -0.13
    lays
    -0.13
    uju
    -0.13
    jte
    -0.13
     certain
    -0.13
    ushman
    -0.13
    POSITIVE LOGITS
     years
    0.19
    年度
    0.18
     months
    0.15
     year
    0.15
    624
    0.14
    gener
    0.14
     decade
    0.14
     decades
    0.14
     month
    0.14
     generation
    0.14
    Act Density 0.047%

    No Known Activations