INDEX
    Explanations

    instances of the word "then" as a temporal marker in the text

    New Auto-Interp
    Negative Logits
     Harlow
    -0.77
     Newsom
    -0.73
     Irm
    -0.73
     ejus
    -0.71
     Marge
    -0.70
    лися
    -0.70
     Vip
    -0.70
     Folsom
    -0.69
     Winfrey
    -0.69
     Bär
    -0.69
    POSITIVE LOGITS
     then
    1.65
     THEN
    1.63
    THEN
    1.56
     Then
    1.47
    then
    1.43
    Then
    1.39
     entonces
    1.25
    dann
    1.17
    Entonces
    1.15
     então
    1.13
    Act Density 0.082%

    No Known Activations