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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    嫁
    -0.07
    :Get
    -0.07
    _suite
    -0.07
    tero
    -0.07
    师兄
    -0.07
    ,Z
    -0.07
    御
    -0.07
    der
    -0.07
    女士
    -0.07
    说道
    -0.06
    POSITIVE LOGITS
     Dayton
    0.08
     Goals
    0.07
    External
    0.07
    吃得
    0.07
     drunken
    0.07
     Graves
    0.07
    _checks
    0.07
     BBB
    0.07
    Navigation
    0.06
     preference
    0.06
    Act Density 0.002%

    No Known Activations