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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     consente
    0.99
    за
    0.87
    이나
    0.86
     disequ
    0.82
    थान
    0.82
    са
    0.81
    ь
    0.79
     foll
    0.79
    я
    0.79
    파
    0.77
    POSITIVE LOGITS
     человеку
    0.72
    лены
    0.72
     solidaridad
    0.70
     علم
    0.69
    OAuth
    0.68
     ortak
    0.67
    arono
    0.67
    antro
    0.66
    igrant
    0.66
     antisymmetric
    0.66
    Act Density 0.001%

    No Known Activations