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

    Neuronpedia

    INDEX
    Explanations

    references to influential women and their contributions or societal roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \<^
    -0.15
    enos
    -0.15
    .ISupportInitialize
    -0.15
    stab
    -0.14
    ιακ
    -0.14
    ικα
    -0.14
    :".$
    -0.13
    enis
    -0.13
    iteli
    -0.13
    ÏĦει
    -0.13
    POSITIVE LOGITS
    ;
    0.18
    );
    0.18
    ï¼īãĢģ
    0.17
    ”;
    0.17
    ;↵
    0.17
     nor
    0.16
    )ãĢģ
    0.16
     );
    0.16
     [];
    0.15
    ];
    0.15
    Act Density 0.641%

    No Known Activations