INDEX
    Explanations

    instances of violence, particularly related to looting and destruction

    New Auto-Interp
    Negative Logits
    amd
    -0.15
    jni
    -0.15
     suites
    -0.15
     Crack
    -0.14
    ãĤ¸ãĥ£
    -0.14
    isans
    -0.14
    owler
    -0.14
    SizeMode
    -0.14
    affles
    -0.14
     quint
    -0.14
    POSITIVE LOGITS
     Neu
    0.17
    rap
    0.16
    loh
    0.15
    .vertx
    0.15
    Bes
    0.14
     Rush
    0.14
    rung
    0.14
     Replay
    0.14
    ipient
    0.13
     impe
    0.13
    Act Density 0.126%

    No Known Activations