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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Set
    -0.07
     Pole
    -0.07
    belief
    -0.07
     flair
    -0.07
     caps
    -0.07
     residence
    -0.07
    (Column
    -0.06
    uft
    -0.06
    Autor
    -0.06
    全体
    -0.06
    POSITIVE LOGITS
    맙
    0.07
    تحرك
    0.07
    鼬
    0.07
    すでに
    0.07
    Tw
    0.07
    ında
    0.07
    ))))↵
    0.07
    ampilkan
    0.06
    消灭
    0.06
     lavor
    0.06
    Act Density 0.012%

    No Known Activations