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

    Neuronpedia

    INDEX
    Explanations

    attributes related to authenticity and properness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ire
    -0.15
    éĨĴ
    -0.14
     lon
    -0.14
    端
    -0.13
    etto
    -0.13
    ä¿¡
    -0.13
     Hath
    -0.13
     redd
    -0.13
     additional
    -0.13
     resil
    -0.13
    POSITIVE LOGITS
    æŁĦ
    0.15
    proper
    0.15
    onen
    0.15
    ayne
    0.15
    itesse
    0.15
    .unregister
    0.14
    dy
    0.14
    auc
    0.14
    addir
    0.14
    enance
    0.14
    Act Density 0.342%

    No Known Activations