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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    태
    -0.08
     subtle
    -0.08
    묵
    -0.07
    험
    -0.07
    🎇
    -0.07
     Saúde
    -0.07
    厨师
    -0.07
     sản
    -0.07
     birth
    -0.07
     insect
    -0.07
    POSITIVE LOGITS
    (',')↵
    0.08
    写的
    0.07
     parentheses
    0.07
    十余年
    0.07
    esion
    0.06
    olib
    0.06
    趙
    0.06
    //---------------------------------------------------------------------------↵↵
    0.06
    lesi
    0.06
     Intercept
    0.06
    Act Density 0.001%

    No Known Activations