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

    Neuronpedia

    INDEX
    Explanations

    references to "dead" in various contexts

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

    dead concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.61
     AssemblyCompany
    -0.59
    IntoConstraints
    -0.58
    ftagPool
    -0.56
    LEncoder
    -0.54
     NSCoder
    -0.54
    TagMode
    -0.52
    BagConstraints
    -0.51
    figer
    -0.49
     ujednoznacz
    -0.49
    POSITIVE LOGITS
     dead
    1.55
    dead
    1.43
    Dead
    1.41
     Dead
    1.38
     DEAD
    1.27
    DEAD
    1.20
     muerta
    0.95
     muerto
    0.94
     muertos
    0.93
     мерт
    0.93
    Act Density 0.021%

    No Known Activations