INDEX
    Explanations

    references to significant occurrences or actions within the text

    New Auto-Interp
    Negative Logits
    ãĤ
    -0.14
    ength
    -0.14
    ernes
    -0.14
    uhn
    -0.14
    ylland
    -0.14
    qw
    -0.14
    нож
    -0.14
    AMPLE
    -0.14
    AZY
    -0.14
    eriod
    -0.13
    POSITIVE LOGITS
     events
    0.23
     happen
    0.20
    events
    0.20
     Events
    0.19
    Events
    0.18
     happened
    0.17
     happening
    0.17
    -events
    0.17
     aconte
    0.16
     happens
    0.15
    Act Density 0.078%

    No Known Activations