INDEX
    Explanations

    terms related to social and economic inequalities

    New Auto-Interp
    Negative Logits
    ardown
    -0.19
    vern
    -0.19
    uel
    -0.17
    ModelProperty
    -0.15
    egend
    -0.15
    onga
    -0.15
    象
    -0.15
    RuleContext
    -0.14
    cott
    -0.14
    arde
    -0.14
    POSITIVE LOGITS
     alike
    0.16
     Bark
    0.15
     Osborne
    0.14
    tam
    0.14
    enti
    0.14
    ta
    0.14
    Tam
    0.14
     tam
    0.13
    ict
    0.13
    chest
    0.13
    Act Density 0.135%

    No Known Activations