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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    дцать
    0.94
    tres
    0.90
    tweets
    0.88
    ческих
    0.86
    oğlu
    0.86
    бен
    0.84
    તિ
    0.82
    ள்ளார்
    0.82
    ます
    0.81
    e
    0.81
    POSITIVE LOGITS
    erweise
    1.07
    isin
    0.93
    anned
    0.89
    งาม
    0.89
    с
    0.88
    সজ্জিত
    0.86
    👍
    0.84
     ढंग
    0.83
    [(\
    0.82
     suited
    0.82
    Act Density 2.340%

    No Known Activations