INDEX
    Explanations

    terms related to military units, such as infantry and cavalry

    references to military and transportation entities

    New Auto-Interp
    Negative Logits
    atis
    -0.78
    umble
    -0.70
    ñ
    -0.65
    abase
    -0.64
    ptions
    -0.64
    ntil
    -0.63
    anyahu
    -0.63
    ilitarian
    -0.61
    gur
    -0.60
    ulet
    -0.60
    POSITIVE LOGITS
    ett
    0.86
    ipeg
    0.78
    raft
    0.76
    hire
    0.74
    issance
    0.73
    layer
    0.73
    obal
    0.70
    NetMessage
    0.69
    acters
    0.69
    lihood
    0.69
    Act Density 0.096%

    No Known Activations