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

    Neuronpedia

    INDEX
    Explanations

    references to safety measures and protective structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MIC
    -0.06
     wheel
    -0.06
     vessel
    -0.06
     hairs
    -0.06
     Wheel
    -0.06
     marble
    -0.06
    ÏĦαν
    -0.06
     silica
    -0.06
    Sink
    -0.06
     gens
    -0.06
    POSITIVE LOGITS
     fence
    0.10
     Fence
    0.09
     Posts
    0.09
     posts
    0.09
     gate
    0.09
     installer
    0.09
    agrid
    0.09
    Posts
    0.09
    _fence
    0.08
     gates
    0.08
    Act Density 0.003%

    No Known Activations