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

    Neuronpedia

    INDEX
    Explanations

    elements related to logical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.48
    Ùĩ
    -0.23
    ska
    -0.20
    ister
    -0.17
    sik
    -0.17
    न
    -0.17
    sah
    -0.17
    sian
    -0.16
    p
    -0.16
    sie
    -0.16
    POSITIVE LOGITS
    à¹ĥà¸Ī
    0.18
    æĢ§çļĦ
    0.18
    aris
    0.14
    о
    0.14
     consc
    0.14
    atre
    0.14
    urma
    0.14
    Vien
    0.14
    ORY
    0.14
     """.
    0.13
    Act Density 0.162%

    No Known Activations