INDEX
    Explanations

    asking about specific aspects of entities

    New Auto-Interp
    Negative Logits
     different
    0.94
     or
    0.94
     kinds
    0.93
     some
    0.88
     types
    0.88
     Types
    0.87
     specify
    0.87
     say
    0.83
    Types
    0.82
     specific
    0.80
    POSITIVE LOGITS
     نہایت
    0.97
    യായിരുന്നു
    0.96
    urations
    0.95
    そして
    0.93
     ইহাদের
    0.93
    无比
    0.92
     অত্যন্ত
    0.91
    这两
    0.90
     ત્યારબાદ
    0.90
    ,—
    0.88
    Act Density 0.051%

    No Known Activations