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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MethodManager
    -0.15
    ãĥ¼ãĥī
    -0.15
    tring
    -0.15
    onta
    -0.15
    ágina
    -0.14
    à¹ĭ
    -0.14
    ings
    -0.14
     features
    -0.13
    DataReader
    -0.13
    ÑĬ
    -0.13
    POSITIVE LOGITS
    all
    0.15
    053
    0.15
    907
    0.15
    éŁ¿
    0.15
    allen
    0.14
     gá»ijc
    0.14
    imed
    0.13
    inger
    0.13
    ĮĢ
    0.13
    adow
    0.13
    Act Density 0.007%

    No Known Activations