INDEX
    Explanations

    sentence terminators and new sentence starts

    New Auto-Interp
    Negative Logits
     glances
    0.39
     beispielsweise
    0.39
    роне
    0.38
    rzez
    0.37
     sepan
    0.35
    ведена
    0.35
    犹如
    0.35
     fréquentes
    0.35
     például
    0.35
    Dequeue
    0.34
    POSITIVE LOGITS
     gồm
    0.52
     Includes
    0.51
     beserta
    0.45
     There
    0.45
    ley
    0.43
    0.43
    up
    0.42
     terdiri
    0.41
    ji
    0.40
    irt
    0.40
    Act Density 0.197%

    No Known Activations