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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     לרא
    -0.07
    ۂ
    -0.07
     +↵↵
    -0.07
     countdown
    -0.07
    ㅒ
    -0.06
    -Clause
    -0.06
    ’:
    -0.06
    ripp
    -0.06
    三条
    -0.06
    偻
    -0.06
    POSITIVE LOGITS
    瑕
    0.07
    ula
    0.07
     оригинал
    0.07
     PictureBox
    0.07
     Psychology
    0.07
    尽力
    0.07
    elfare
    0.07
    皙
    0.06
     Beach
    0.06
    {}↵
    0.06
    Act Density 0.001%

    No Known Activations