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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ed
    0.93
    苣
    0.93
    Vale
    0.89
    Unlike
    0.87
    Generating
    0.86
    Token
    0.84
    Ella
    0.84
    Duck
    0.84
    Replacement
    0.83
    Dalam
    0.83
    POSITIVE LOGITS
    خرى
    1.05
    на
    1.03
    ي
    1.03
    j
    1.02
     esperienza
    0.99
    可能的
    0.98
    י
    0.98
    宜
    0.97
    抨
    0.97
    しまう
    0.96
    Act Density 0.000%

    No Known Activations