INDEX
    Explanations

    phrases and vocabulary associated with rumors and speculation

    New Auto-Interp
    Negative Logits
    rientation
    -0.17
     Replay
    -0.14
    unexpected
    -0.13
    avra
    -0.13
    _cpus
    -0.13
    ocus
    -0.13
    acon
    -0.13
    IENTATION
    -0.12
     дÑĥÑĪ
    -0.12
    entai
    -0.12
    POSITIVE LOGITS
     reports
    0.46
     rumors
    0.42
    rum
    0.39
     rumours
    0.38
     rumor
    0.38
     speculation
    0.37
     spec
    0.36
    reports
    0.36
     Reports
    0.36
     rum
    0.36
    Act Density 0.233%

    No Known Activations