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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pueden
    -0.09
    -has
    -0.07
    讓他
    -0.07
    ن
    -0.07
    -0.07
    	make
    -0.06
     please
    -0.06
     sie
    -0.06
    (SDL
    -0.06
     moeten
    -0.06
    POSITIVE LOGITS
    环保
    0.07
     Thief
    0.07
     totalTime
    0.07
     efficiency
    0.07
    brahim
    0.07
     Reynolds
    0.07
     Protection
    0.06
    readOnly
    0.06
     affordable
    0.06
    完好
    0.06
    Act Density 0.005%

    No Known Activations