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

    Neuronpedia

    INDEX
    Explanations

    apostrophes and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FINE
    -0.15
    ayo
    -0.15
    ******↵↵
    -0.14
    âĢ¢↵↵
    -0.14
    abis
    -0.13
    à¸Ĺย
    -0.13
     jadx
    -0.13
    achs
    -0.13
    ArrayType
    -0.13
     Platt
    -0.13
    POSITIVE LOGITS
     etc
    0.19
    etc
    0.15
    cer
    0.15
     \↵
    0.15
    pedo
    0.15
     ↵
    0.14
     Corner
    0.14
     corner
    0.14
    ardown
    0.14
    침
    0.14
    Act Density 0.017%

    No Known Activations