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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and formal notation related to variables and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.65
     estekak
    -0.65
     autorytatywna
    -0.62
     kasarigan
    -0.62
    +#+
    -0.60
    UserScript
    -0.60
     Савезне
    -0.59
     مشين
    -0.58
    Rüyada
    -0.56
     ویکی‌پدی
    -0.56
    POSITIVE LOGITS
     start
    0.54
     beginning
    0.52
     lowest
    0.50
     mulai
    0.49
    start
    0.49
     earliest
    0.46
     starting
    0.45
    Start
    0.45
     dimulai
    0.45
     시작
    0.44
    Act Density 0.536%

    No Known Activations