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

    Neuronpedia

    INDEX
    Explanations

    references to academic articles and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aten
    -0.15
    па
    -0.15
     hinter
    -0.15
    ensen
    -0.15
    lij
    -0.15
    ÙĦÙī
    -0.15
    огÑĢа
    -0.14
    ustr
    -0.14
    uze
    -0.14
    lez
    -0.14
    POSITIVE LOGITS
    ARA
    0.19
    аÑĢа
    0.19
    ulin
    0.18
    аÑĢов
    0.14
     ìĺ
    0.14
    atta
    0.14
    Äħd
    0.14
    Quit
    0.14
    aldi
    0.14
    ration
    0.14
    Act Density 0.004%

    No Known Activations