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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their corresponding structure in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xaf
    -0.21
     McDon
    -0.17
    ucus
    -0.16
     needles
    -0.14
     pride
    -0.14
    osy
    -0.14
    ohn
    -0.14
    aption
    -0.13
    plusplus
    -0.13
    наÑĤ
    -0.13
    POSITIVE LOGITS
    ritch
    0.17
    TestFixture
    0.14
    -des
    0.14
    çĤ
    0.14
    REFERRED
    0.14
    obook
    0.14
    yz
    0.14
    VK
    0.13
    bara
    0.13
    PM
    0.13
    Act Density 0.391%

    No Known Activations