INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    PLICATION
    0.44
     caveats
    0.44
     totiž
    0.43
     either
    0.43
     też
    0.42
     übrigens
    0.41
     contexts
    0.41
     volition
    0.41
    וריה
    0.41
     också
    0.40
    POSITIVE LOGITS
     Which
    1.10
    Which
    1.04
     کدام
    0.98
     WHICH
    0.82
    which
    0.81
     nào
    0.81
    哪个
    0.79
     which
    0.79
     ______
    0.76
     ________
    0.74
    Act Density 0.007%

    No Known Activations