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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     energ
    -0.07
    _YES
    -0.07
    osen
    -0.07
     VP
    -0.06
     Literal
    -0.06
    娃
    -0.06
    팃
    -0.06
    ningen
    -0.06
    为一体的
    -0.06
     MTV
    -0.06
    POSITIVE LOGITS
     arranged
    0.07
    (order
    0.07
     groups
    0.07
    0.06
     hills
    0.06
     riê
    0.06
     Mage
    0.06
     Rwanda
    0.06
     Surface
    0.06
    浮
    0.06
    Act Density 0.004%

    No Known Activations