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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns and titles, particularly those related to human rights and significant individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urette
    -0.15
    úc
    -0.14
    Generated
    -0.14
    ắn
    -0.14
    oren
    -0.13
    idue
    -0.13
    .cf
    -0.13
    üm
    -0.13
    ẩu
    -0.13
     Ec
    -0.13
    POSITIVE LOGITS
     cl
    0.15
    Fallback
    0.14
     scre
    0.14
     spe
    0.13
     Wen
    0.13
    Äħ
    0.13
    ãĥ¼ãĥ©
    0.12
     Duy
    0.12
     Mills
    0.12
    ought
    0.12
    Act Density 0.273%

    No Known Activations