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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     kell
    -0.08
     Gott
    -0.07
     oggi
    -0.07
     ordinal
    -0.07
    哲学
    -0.07
    owed
    -0.07
     מת
    -0.07
    (ws
    -0.07
    (full
    -0.07
     כאשר
    -0.07
    POSITIVE LOGITS
    �
    0.07
    绢
    0.07
    撼
    0.07
    峛
    0.07
    宝妈
    0.07
    赗
    0.06
    瑝
    0.06
    桄
    0.06
    𫓹
    0.06
    俫
    0.06
    Act Density 0.094%

    No Known Activations