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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     diff
    -0.07
    重要指示
    -0.07
    TEXT
    -0.06
    מטה
    -0.06
    ☈
    -0.06
    中小学
    -0.06
    Address
    -0.06
     mornings
    -0.06
    ניוז
    -0.06
    /books
    -0.06
    POSITIVE LOGITS
    ˆ
    0.07
    嬷
    0.07
     Boots
    0.07
     //</
    0.07
    保守
    0.07
     especial
    0.07
     occupations
    0.07
     часов
    0.07
    جاب
    0.07
     Luxembourg
    0.07
    Act Density 0.233%

    No Known Activations