INDEX
    Explanations

    mentions of legal terms such as defendant, security guards, and disputes

    terms related to accusations

    New Auto-Interp
    Negative Logits
     prag
    -0.72
     seeded
    -0.66
     Niet
    -0.62
     LX
    -0.61
     messaging
    -0.61
     Huck
    -0.61
     sidebar
    -0.60
     monarchy
    -0.59
     queer
    -0.59
     paved
    -0.58
    POSITIVE LOGITS
    acc
    4.67
    Acc
    1.71
    ACC
    1.68
    acci
    1.59
     Acc
    1.46
    acca
    1.38
    acco
    1.28
     acc
    1.19
    ac
    1.17
    ucc
    1.14
    Act Density 0.008%

    No Known Activations