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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of purity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orp
    -0.17
    ether
    -0.15
    lar
    -0.15
    edn
    -0.14
    shelf
    -0.14
    åĬ¡
    -0.14
    yth
    -0.14
    æ£ĭ
    -0.13
    ÑĢÑĥÑģ
    -0.13
    okt
    -0.13
    POSITIVE LOGITS
    auc
    0.19
    -blood
    0.18
    纯
    0.18
    ¢åįķ
    0.17
     Pure
    0.17
    ç²
    0.17
    pure
    0.17
    bred
    0.16
    à¹Ĩ
    0.16
    folio
    0.16
    Act Density 0.017%

    No Known Activations