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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Transactions
    -0.07
    .isEnabled
    -0.07
     Klaus
    -0.07
     semantic
    -0.06
     restaurants
    -0.06
     lưng
    -0.06
    erto
    -0.06
    䴕
    -0.06
     Syndrome
    -0.06
    臺南
    -0.06
    POSITIVE LOGITS
     חוות
    0.07
    ໃ
    0.06
     ignition
    0.06
    IVITY
    0.06
     adopted
    0.06
    痊
    0.06
    allowed
    0.06
    :
↵
    0.06
     gri
    0.06
     outcomes
    0.06
    Act Density 0.006%

    No Known Activations