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

    Neuronpedia

    INDEX
    Explanations

    sections and subsections in a structured document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    大åħ¨
    -0.16
    esseract
    -0.14
    inges
    -0.14
    оÑģÑĤаÑĤ
    -0.14
     Tong
    -0.14
    agic
    -0.14
    æĥij
    -0.13
    çľł
    -0.13
    ãĥ³ãĥĸ
    -0.13
    ledo
    -0.13
    POSITIVE LOGITS
     introduction
    0.39
     Introduction
    0.38
    Introduction
    0.36
     introdu
    0.29
     introduced
    0.25
     introduce
    0.25
    Conclusion
    0.23
    roduction
    0.22
     introducing
    0.22
     acknowled
    0.22
    Act Density 0.024%

    No Known Activations