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

    Neuronpedia

    INDEX
    Explanations

    references to scientific methods or discussions about research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acos
    -0.56
    __*/
    -0.50
    ContextHolder
    -0.49
     لكرة
    -0.49
     acos
    -0.46
     planer
    -0.44
    nace
    -0.44
     Вікі
    -0.43
    ้อง
    -0.43
     paperwork
    -0.43
    POSITIVE LOGITS
     review
    1.36
    review
    1.27
    Review
    1.27
     Review
    1.24
     reviewed
    1.23
     reviews
    1.23
    reviewed
    1.17
     reviewing
    1.15
     REVIEW
    1.06
     Reviews
    1.04
    Act Density 0.887%

    No Known Activations