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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    火灾
    -0.08
    emergency
    -0.08
     attract
    -0.08
     פעולה
    -0.08
    roduce
    -0.08
     Applied
    -0.07
     pornography
    -0.07
    鸪
    -0.07
     дор
    -0.07
    foreach
    -0.07
    POSITIVE LOGITS
     excludes
    0.08
    주의
    0.07
    _study
    0.07
     clases
    0.07
    kategori
    0.07
     (_.
    0.07
    יבו
    0.07
    aan
    0.06
    ające
    0.06
     кан
    0.06
    Act Density 0.001%

    No Known Activations