INDEX
    Explanations

    words related to human rights and social justice issues

    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.05
    3:0.06
    4:0.03
    5:0.38
    6:0.06
    7:0.01
    8:0.15
    9:0.08
    10:0.05
    11:0.03
    Negative Logits
     jug
    -1.50
     lives
    -1.46
     stable
    -1.43
     Starship
    -1.39
    ewater
    -1.36
    racuse
    -1.35
     Host
    -1.33
     Unic
    -1.30
     Helic
    -1.29
    utable
    -1.29
    POSITIVE LOGITS
    1.65
    echo
    1.64
    arte
    1.56
    draft
    1.54
    forums
    1.53
    enko
    1.53
    include
    1.52
    course
    1.47
    ax
    1.44
    1.43
    Act Density 0.130%

    No Known Activations