INDEX
    Explanations

    discussions about privilege and how it affects individuals and society

    New Auto-Interp
    Negative Logits
    aring
    -0.17
    isol
    -0.15
    ÑĥÑĩа
    -0.15
     Walsh
    -0.15
    jerne
    -0.14
    ÑĢади
    -0.14
    .AD
    -0.14
    ish
    -0.14
    cw
    -0.14
    tracts
    -0.13
    POSITIVE LOGITS
    ously
    0.18
    oldemort
    0.16
     ******************************************************************************↵
    0.15
    klad
    0.15
    perf
    0.15
    ÑĤим
    0.15
    каз
    0.14
    SingleNode
    0.14
    ouse
    0.14
    visor
    0.14
    Act Density 0.009%

    No Known Activations