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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their various arrangements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ฝ
    -0.62
     przec
    -0.61
    Luther
    -0.60
     Goul
    -0.59
    vl
    -0.58
    n
    -0.57
     tuyến
    -0.57
     Câ
    -0.55
    Ess
    -0.55
    ing
    -0.54
    POSITIVE LOGITS
    __':
    1.31
    __':
    1.17
    __":
    1.16
    ']))
    1.14
    __":
    1.09
    ']))
    1.09
    '])){
    1.07
    ]")]
    1.04
    ])]
    1.04
    )»
    1.03
    Act Density 0.083%

    No Known Activations