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

    Neuronpedia

    INDEX
    Explanations

    references to rights and the concept of correctness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McKinnon
    -1.01
    Hauptartikel
    -0.96
    matchCondition
    -0.87
    NameInMap
    -0.84
     okuyayım
    -0.83
    期刊论文
    -0.82
    __":
    -0.81
    oredCriteria
    -0.81
    CMYK
    -0.80
     Tas
    -0.79
    POSITIVE LOGITS
    right
    1.35
     RIGHT
    1.32
     Right
    1.29
    Right
    1.25
     right
    1.24
    RIGHT
    1.23
    setRight
    1.13
    getRight
    1.10
     righ
    1.05
     Righ
    0.96
    Act Density 0.137%

    No Known Activations