INDEX
    Explanations

    punctuation, particularly periods

    New Auto-Interp
    Negative Logits
    eck
    -0.15
    ionales
    -0.15
    resse
    -0.15
    Ø©
    -0.15
     Thrones
    -0.14
     Neb
    -0.14
    olo
    -0.14
    и
    -0.14
    AllWindows
    -0.14
     gsi
    -0.14
    POSITIVE LOGITS
     Nullable
    0.16
    noinspection
    0.15
    βολ
    0.14
    हन
    0.14
    ëĭĪìķĦ
    0.13
    uddy
    0.13
    sword
    0.13
    uler
    0.13
     Chen
    0.12
    610
    0.12
    Act Density 0.077%

    No Known Activations