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

    Neuronpedia

    INDEX
    Explanations

    numerical data types and their associated values in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LETTE
    -0.15
    lası
    -0.14
     Berk
    -0.14
    culo
    -0.14
    ment
    -0.14
    addError
    -0.14
    æģ¯
    -0.14
    ÃŃnh
    -0.14
    chai
    -0.14
    avax
    -0.14
    POSITIVE LOGITS
     Kral
    0.17
    eri
    0.15
     punishable
    0.14
    279
    0.14
     Accom
    0.14
     Chamber
    0.14
    675
    0.13
    asco
    0.13
    zilla
    0.13
    :"-
    0.13
    Act Density 0.021%

    No Known Activations