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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    讥
    -0.07
    衅
    -0.07
     changes
    -0.07
    冏
    -0.07
     Petroleum
    -0.07
    学问
    -0.07
     entrepreneurial
    -0.07
     imprison
    -0.07
    愧
    -0.06
    mailto
    -0.06
    POSITIVE LOGITS
     flat
    0.08
    dry
    0.08
     Belly
    0.07
     ל
    0.07
     Dro
    0.07
    แผ
    0.07
    (dataset
    0.07
     disg
    0.07
     dist
    0.07
    ();↵↵↵
    0.07
    Act Density 0.025%

    No Known Activations