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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    自己
    0.57
     monotonically
    0.57
    很好的
    0.57
     castes
    0.57
    但是
    0.56
    好像
    0.55
     operands
    0.54
     rato
    0.54
     vignettes
    0.53
    して
    0.52
    POSITIVE LOGITS
     Dopo
    0.82
     —
    0.79
     JPMorgan
    0.77
     Selon
    0.74
     заявил
    0.74
     Một
    0.73
     Mientras
    0.71
     Pat
    0.71
     Công
    0.71
     Mentre
    0.71
    Act Density 0.000%

    No Known Activations