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

    Neuronpedia

    INDEX
    Explanations

    specific keywords related to measurable attributes or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hack
    -0.15
    endent
    -0.15
    readcr
    -0.14
    aille
    -0.14
    avel
    -0.14
    शà¤ķ
    -0.13
    âĢŀV
    -0.13
    349
    -0.13
    adius
    -0.13
     Schneider
    -0.13
    POSITIVE LOGITS
    REE
    0.15
    اÙģÙĤ
    0.15
     pri
    0.14
     æĹ
    0.14
     Hanna
    0.14
    аÑĦ
    0.14
    orz
    0.14
    itage
    0.14
    ajas
    0.13
    __$
    0.13
    Act Density 0.052%

    No Known Activations