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

    Neuronpedia

    INDEX
    Explanations

    numeric references and citations in academic articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arro
    -0.15
     Surg
    -0.15
    lix
    -0.15
    lify
    -0.14
    atura
    -0.14
     îł
    -0.14
     Sund
    -0.14
    ναν
    -0.14
    lama
    -0.14
    aná
    -0.13
    POSITIVE LOGITS
    _HP
    0.15
    æk
    0.14
    dez
    0.14
    ìĭ¬
    0.14
    isin
    0.14
    ormal
    0.14
    .InnerException
    0.14
    ÑĢаÑī
    0.13
    andard
    0.13
    çį
    0.13
    Act Density 0.002%

    No Known Activations