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

    Neuronpedia

    INDEX
    Explanations

    key-value pairs in structured data or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¹ģà¸ŀ
    -0.15
    ikan
    -0.14
    chart
    -0.14
    maz
    -0.13
    åľĴ
    -0.13
     Reds
    -0.13
    20
    -0.13
     Arabian
    -0.13
     Surg
    -0.13
    úsqueda
    -0.13
    POSITIVE LOGITS
    alary
    0.17
    _MAGIC
    0.15
    Writes
    0.15
    LOPT
    0.15
    ierz
    0.14
    abwe
    0.14
    ²
    0.14
    _MISS
    0.14
    ë¹ĦìĬ¤
    0.14
    Persistence
    0.13
    Act Density 0.013%

    No Known Activations