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

    Neuronpedia

    INDEX
    Explanations

    numbers, particularly years or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aina
    -0.17
    ritt
    -0.15
    eru
    -0.15
    lez
    -0.14
    atur
    -0.14
    amenti
    -0.14
    auction
    -0.14
    ano
    -0.14
    ament
    -0.14
    oru
    -0.13
    POSITIVE LOGITS
    Burn
    0.16
    zeros
    0.15
    sta
    0.15
    ibble
    0.14
    loys
    0.14
    ross
    0.14
    loe
    0.14
     Char
    0.14
    nings
    0.14
    anik
    0.14
    Act Density 0.019%

    No Known Activations