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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atur
    -0.18
    fal
    -0.18
    ve
    -0.17
    arter
    -0.15
    im
    -0.15
    ae
    -0.14
    azzi
    -0.14
    .gov
    -0.14
    igmoid
    -0.14
    itesse
    -0.14
    POSITIVE LOGITS
    ÑģÑĤоÑĢ
    0.23
    аков
    0.18
    story
    0.17
    ÑĢониÑĩеÑģ
    0.17
    зд
    0.17
    ÑģÑĤин
    0.17
    ноп
    0.16
    stor
    0.16
    ÏĥÏĦο
    0.16
    érica
    0.16
    Act Density 0.010%

    No Known Activations