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

    Neuronpedia

    INDEX
    Explanations

    Instructions, opinions

    np_max-act · gemini-2.0-flash

    The neuron flags instructional language that guides users to carry out unsafe, unethical, or otherwise disallowed actions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    any mention of dangerous or harmful activities and issues surrounding consent and ethics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .URL
    -0.07
    top
    -0.07
    Frequency
    -0.07
     synergy
    -0.06
     Houses
    -0.06
     Sections
    -0.06
     benchmark
    -0.06
    Orders
    -0.06
    fish
    -0.06
     Velocity
    -0.06
    POSITIVE LOGITS
     dern
    0.08
    amız
    0.07
    ']?>"
    0.06
     اما
    0.06
     trough
    0.06
     극
    0.06
     siyas
    0.06
     aktif
    0.06
    imiz
    0.06
     ขนาด
    0.06
    Act Density 0.041%

    No Known Activations