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

    Neuronpedia

    INDEX
    Explanations

    opening and closing brackets in code or structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uisse
    -0.16
    icros
    -0.16
     unary
    -0.14
    arme
    -0.14
    zan
    -0.14
    "https
    -0.13
    bourg
    -0.13
    xm
    -0.13
    Ñĩе
    -0.13
     اÙĤ
    -0.13
    POSITIVE LOGITS
    urs
    0.15
    egr
    0.15
     Bucc
    0.14
    erland
    0.14
    ucz
    0.14
    .synthetic
    0.14
    ancock
    0.14
     Westbrook
    0.13
     Yard
    0.13
     Marble
    0.13
    Act Density 0.030%

    No Known Activations