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

    Neuronpedia

    INDEX
    Explanations

    terms related to life and death

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

    death or to die, always

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.68
    parsedMessage
    -0.60
     للمعارف
    -0.58
    CppMethod
    -0.55
    DataAnnotations
    -0.54
    EqualTo
    -0.54
     ***!
    -0.52
     theils
    -0.50
     Administrativna
    -0.49
     equivalently
    -0.49
    POSITIVE LOGITS
    走
    1.94
     走
    1.61
    走的
    1.06
    走了
    1.01
    走り
    0.73
     walk
    0.69
    走到
    0.69
    走る
    0.69
     walked
    0.68
    walk
    0.68
    Act Density 0.002%

    No Known Activations