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

    Neuronpedia

    INDEX
    Explanations

    references to user policy validation cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oa
    -0.15
    ERE
    -0.14
    ophile
    -0.14
     readme
    -0.14
    pon
    -0.14
    è¸
    -0.14
    ARN
    -0.14
    ium
    -0.14
    din
    -0.14
    paren
    -0.13
    POSITIVE LOGITS
    quoise
    0.17
    azor
    0.16
    537
    0.15
    омина
    0.15
     INLINE
    0.15
    oÄŁ
    0.15
    olit
    0.15
    icha
    0.14
    chwitz
    0.14
    HeaderCode
    0.14
    Act Density 0.026%

    No Known Activations