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

    Neuronpedia

    INDEX
    Explanations

    references to warnings or concerns about societal issues, particularly regarding health and corporate influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĮĻ
    -0.17
     EXIT
    -0.16
    EXIT
    -0.15
     ÙĦغ
    -0.15
     bì
    -0.14
    arin
    -0.14
    empor
    -0.14
    ÙĪدÙĩ
    -0.14
    ingu
    -0.13
    vault
    -0.13
    POSITIVE LOGITS
    aget
    0.16
    atron
    0.16
     bust
    0.15
     bulunuyor
    0.14
    classpath
    0.14
    antan
    0.14
    adoras
    0.13
     unde
    0.13
    ónica
    0.13
    ë¹Ī
    0.13
    Act Density 0.192%

    No Known Activations