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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    闸
    -0.07
    וב
    -0.07
    북
    -0.07
    工业大学
    -0.07
    번
    -0.07
     cushion
    -0.06
    在这
    -0.06
     Reviewed
    -0.06
    冁
    -0.06
    nero
    -0.06
    POSITIVE LOGITS
    :'+
    0.08
    _aliases
    0.07
    recipient
    0.07
    _styles
    0.07
     affair
    0.07
    -tone
    0.07
     refin
    0.06
    YYYY
    0.06
    ⚗
    0.06
    %
    0.06
    Act Density 0.059%

    No Known Activations