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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Feng
    -0.08
     cynical
    -0.07
     ska
    -0.07
     INSTALL
    -0.07
    🥵
    -0.07
    佬
    -0.07
    倾向于
    -0.07
     którzy
    -0.07
     gaussian
    -0.07
     genuinely
    -0.07
    POSITIVE LOGITS
    有關
    0.08
    _base
    0.07
     можно
    0.07
     complexity
    0.07
    𝑋
    0.07
     texto
    0.07
     relate
    0.07
    _To
    0.07
     renaming
    0.07
    магаз
    0.07
    Act Density 0.009%

    No Known Activations