INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     स्त्री
    0.72
     Fontana
    0.71
     Tisch
    0.71
    लाइ
    0.70
     이벤트
    0.70
    ခု
    0.69
    hovah
    0.67
    0.67
    வெ
    0.66
    irik
    0.66
    POSITIVE LOGITS
    EPC
    0.87
     maison
    0.84
     frontage
    0.83
     plot
    0.82
     EPC
    0.81
     tenure
    0.77
     rear
    0.76
     Edward
    0.75
    Edward
    0.74
     refurbishment
    0.72
    Act Density 0.040%

    No Known Activations