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

    Neuronpedia

    INDEX
    Explanations

    references to parentheses and brackets in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iard
    -0.07
    iw
    -0.06
    izard
    -0.06
    enberg
    -0.06
    imeter
    -0.06
    urious
    -0.06
    erland
    -0.06
     Deferred
    -0.06
    tras
    -0.06
    ipur
    -0.06
    POSITIVE LOGITS
    ed
    0.08
    ally
    0.07
    lease
    0.07
    ÄĽst
    0.07
    oler
    0.07
    å¼ı
    0.07
    OCR
    0.07
    aux
    0.07
    oret
    0.06
     Bal
    0.06
    Act Density 0.004%

    No Known Activations