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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ßerdem
    -0.07
    寅
    -0.07
    Добав
    -0.06
    白宫
    -0.06
     Ger
    -0.06
    theon
    -0.06
    📬
    -0.06
    蚯
    -0.06
    Shutdown
    -0.06
    odafone
    -0.06
    POSITIVE LOGITS
     pk
    0.08
    Skill
    0.08
     mn
    0.07
    ，
    0.07
    背景
    0.07
     executor
    0.06
    .all
    0.06
    .anchor
    0.06
    }`;↵
    0.06
    谢
    0.06
    Act Density 2.191%

    No Known Activations