INDEX
    Explanations

    references to government or organizational actions related to social issues and policies

    New Auto-Interp
    Negative Logits
    KHTML
    -0.13
     NVIC
    -0.13
    ↵↵
    -0.13
     Fior
    -0.13
    ombine
    -0.12
    adlo
    -0.12
    argas
    -0.12
     Erotische
    -0.12
    olet
    -0.12
    ————
    -0.12
    POSITIVE LOGITS
    misc
    0.14
    .breakpoints
    0.12
    ç¯ī
    0.12
    alis
    0.12
    ingle
    0.12
    cid
    0.11
    iving
    0.11
     Vác
    0.11
    jamin
    0.11
    éĻ£
    0.11
    Act Density 0.224%

    No Known Activations