INDEX
    Explanations

    various forms of the word "boycott" and related terms indicating exclusion or passive interactions

    New Auto-Interp
    Negative Logits
    inz
    -0.16
    ho
    -0.14
    usz
    -0.14
     Widow
    -0.14
    732
    -0.14
    çIJ³
    -0.13
     Dess
    -0.13
     rond
    -0.13
     Lynch
    -0.13
    utz
    -0.13
    POSITIVE LOGITS
    arger
    0.14
    ippers
    0.14
    ancies
    0.13
    ÏĪη
    0.13
    .datab
    0.13
    ÏĦÎŃÏģα
    0.13
    getAs
    0.13
     겨
    0.13
    ÏĦÏį
    0.13
    ÑĤоÑĤ
    0.13
    Act Density 0.012%

    No Known Activations