INDEX
    Explanations

    references to leadership roles and organizational titles

    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.10
    3:0.21
    4:0.01
    5:0.03
    6:0.07
    7:0.12
    8:0.04
    9:0.12
    10:0.05
    11:0.15
    Negative Logits
    inarily
    -1.26
    ateral
    -1.25
    omsky
    -1.25
    soDeliveryDate
    -1.21
    ppo
    -1.20
    utterstock
    -1.20
    iasco
    -1.13
    itored
    -1.12
    killed
    -1.10
    ocr
    -1.10
    POSITIVE LOGITS
     rall
    1.39
    ��
    1.26
     UNESCO
    1.26
     laun
    1.19
    1.19
     KT
    1.17
     CES
    1.14
     ABE
    1.13
     Lanka
    1.10
     Gale
    1.10
    Act Density 0.018%

    No Known Activations