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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    按照
    -0.08
    ∇
    -0.07
    friend
    -0.07
     miners
    -0.07
    CONFIG
    -0.07
    =list
    -0.07
    ENV
    -0.07
    導
    -0.07
    NW
    -0.06
    weapons
    -0.06
    POSITIVE LOGITS
     reputed
    0.08
    垱
    0.08
    玼
    0.08
    (Output
    0.07
    恔
    0.07
    ܀
    0.07
    _DISABLE
    0.07
    ipes
    0.07
    ᕗ
    0.07
    すべ
    0.07
    Act Density 0.007%

    No Known Activations