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

    Neuronpedia

    INDEX
    Explanations

    specific years and numerical references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    747
    -0.15
    ort
    -0.14
    ippi
    -0.14
     Boom
    -0.14
    ubi
    -0.14
     k
    -0.14
     House
    -0.14
     academics
    -0.13
     ass
    -0.13
    æ¯Ľ
    -0.13
    POSITIVE LOGITS
    essler
    0.17
    irst
    0.16
    oya
    0.15
    geb
    0.15
    ież
    0.15
    omers
    0.15
    adu
    0.14
    ghest
    0.14
    iedo
    0.14
    é§
    0.14
    Act Density 0.004%

    No Known Activations