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

    Neuronpedia

    INDEX
    Explanations

    instances of parentheses and their usage in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    however
    -0.18
    Trap
    -0.17
     trap
    -0.15
    Invariant
    -0.15
    acman
    -0.15
     ÏĮμÏīÏĤ
    -0.15
    Äįku
    -0.15
    ëĿ¼ëıĦ
    -0.15
    yll
    -0.14
    addir
    -0.14
    POSITIVE LOGITS
     Noel
    0.15
    Ñĥва
    0.14
    )(_
    0.14
    ami
    0.14
    ioni
    0.14
    oret
    0.14
    orm
    0.14
    ONO
    0.14
    živ
    0.13
     ser
    0.13
    Act Density 0.073%

    No Known Activations