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

    Neuronpedia

    INDEX
    Explanations

    phrases or constructions that indicate responsibility or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by state or description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.46
    WebServlet
    -0.45
     &___
    -0.44
    principalColumn
    -0.40
    ruptedException
    -0.40
     zoll
    -0.38
     fritas
    -0.37
     vuotta
    -0.35
    yntaxException
    -0.34
    saraba
    -0.34
    POSITIVE LOGITS
     للمعارف
    0.66
     ویکی‌پدی
    0.48
    western
    0.45
    brl
    0.45
    CloseOperation
    0.43
    西部
    0.43
    warded
    0.41
    whole
    0.40
    dflare
    0.40
     Profess
    0.40
    Act Density 0.521%

    No Known Activations