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

    Neuronpedia

    INDEX
    Explanations

    references to specific biological classifications or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     огÑĢа
    -0.20
     еÑģÑĤе
    -0.20
     меÑĤалли
    -0.19
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.18
     ÑĢанÑĮ
    -0.18
     ÑģобÑĭ
    -0.18
     поба
    -0.16
    kowski
    -0.16
    ocket
    -0.16
     заболева
    -0.16
    POSITIVE LOGITS
     пÑĢез
    0.20
     Ñģлед
    0.18
     вед
    0.17
     Presidency
    0.17
     tam
    0.17
     ot
    0.17
     поÑĢ
    0.16
    ube
    0.16
    ato
    0.16
     ÐŁÑĢез
    0.16
    Act Density 0.001%

    No Known Activations