INDEX
    Explanations

    promotions and features related to online content subscriptions and events

    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.06
    2:0.10
    3:0.06
    4:0.04
    5:0.12
    6:0.11
    7:0.11
    8:0.09
    9:0.05
    10:0.11
    11:0.08
    Negative Logits
    nown
    -1.49
    ernel
    -1.29
    chwitz
    -1.28
    lyak
    -1.26
    alon
    -1.26
    ivas
    -1.26
    offic
    -1.22
    yang
    -1.21
    cific
    -1.20
    hement
    -1.20
    POSITIVE LOGITS
     archive
    1.50
     curated
    1.31
     Featured
    1.25
     playlist
    1.24
     subscription
    1.24
     essays
    1.18
     Deadline
    1.17
     renaissance
    1.17
     bookmark
    1.15
     rebate
    1.13
    Act Density 0.001%

    No Known Activations