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

    Neuronpedia

    INDEX
    Explanations

    references to academic programs and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    619
    -0.14
    ising
    -0.14
     nowrap
    -0.13
    581
    -0.13
    aru
    -0.13
    591
    -0.12
    ž
    -0.12
    ado
    -0.12
     romant
    -0.12
    872
    -0.12
    POSITIVE LOGITS
     Gloss
    0.14
    alfa
    0.14
     other
    0.14
     Uncategorized
    0.14
    URRED
    0.14
    WEEN
    0.13
    (EFFECT
    0.13
    isol
    0.13
    ¶Į
    0.13
    etc
    0.13
    Act Density 0.066%

    No Known Activations