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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     liberté
    -0.09
    ȗ
    -0.08
    쇱
    -0.07
     Geek
    -0.07
     MLM
    -0.07
     """",↵
    -0.07
    リア
    -0.07
    diğim
    -0.07
     señor
    -0.07
    쭘
    -0.07
    POSITIVE LOGITS
    ali
    0.07
    八字
    0.07
    بل
    0.07
    _digit
    0.07
     devel
    0.07
    קוס
    0.06
    cf
    0.06
    -effect
    0.06
    苍白
    0.06
    abei
    0.06
    Act Density 0.034%

    No Known Activations