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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     אמר
    -0.07
     Dec
    -0.07
    仃
    -0.07
    混沌
    -0.07
    Luke
    -0.07
    城里
    -0.07
     disconnect
    -0.07
     Adds
    -0.07
     كان
    -0.07
     decide
    -0.06
    POSITIVE LOGITS
    ホテ
    0.08
    _periods
    0.07
    .argmax
    0.07
    .Metadata
    0.07
    巴斯
    0.07
    ቡ
    0.06
    行政区
    0.06
    pañ
    0.06
    _CYCLE
    0.06
    ಟ
    0.06
    Act Density 0.012%

    No Known Activations