INDEX
    Explanations

    phrases related to social influence and community responsibilities

    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.26
    3:0.21
    4:0.10
    5:0.03
    6:0.03
    7:0.06
    8:0.05
    9:0.04
    10:0.08
    11:0.05
    Negative Logits
    ril
    -1.40
     coord
    -1.32
    pex
    -1.31
    -1.26
    -1.26
    artments
    -1.24
    gio
    -1.22
    reau
    -1.22
    ede
    -1.18
    rote
    -1.18
    POSITIVE LOGITS
    200000
    1.46
     sake
    1.44
     please
    1.33
     perenn
    1.31
    "],"
    1.30
     adventurous
    1.27
    uctions
    1.24
    please
    1.23
     aspiring
    1.22
     enduring
    1.21
    Act Density 0.147%

    No Known Activations