INDEX
    Explanations

    concepts related to control and agency in relationships

    New Auto-Interp
    Negative Logits
    igure
    -0.16
    .mvp
    -0.16
    sett
    -0.15
     í
    -0.14
    wipe
    -0.14
    ork
    -0.14
    ire
    -0.13
    ï½¢
    -0.13
    wolf
    -0.13
    ERVE
    -0.13
    POSITIVE LOGITS
    .Framework
    0.19
    /control
    0.17
     nor
    0.16
    addon
    0.15
     Control
    0.14
    Control
    0.14
    Launcher
    0.14
    immutable
    0.14
    control
    0.14
    -control
    0.14
    Act Density 0.097%

    No Known Activations