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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Magnitude
    -0.08
    入学
    -0.07
     Slate
    -0.07
    \Active
    -0.07
    Snow
    -0.07
     pow
    -0.06
    /code
    -0.06
     Use
    -0.06
    suming
    -0.06
     Drug
    -0.06
    POSITIVE LOGITS
     NS
    0.07
     oppon
    0.07
    بو
    0.07
    弼
    0.07
     supporter
    0.07
    叫我
    0.06
     Cartesian
    0.06
    _X
    0.06
    说我
    0.06
    ענה
    0.06
    Act Density 0.008%

    No Known Activations