INDEX
    Explanations

    phrases indicating referring or transferring something to another person or entity for further action or consideration

    references to legal or procedural referrals

    New Auto-Interp
    Negative Logits
    pton
    -0.73
     fooled
    -0.73
    apest
    -0.72
    natureconservancy
    -0.71
     dup
    -0.70
    anka
    -0.66
    artifacts
    -0.66
    ble
    -0.65
    ousands
    -0.64
    Supported
    -0.64
    POSITIVE LOGITS
     GitHub
    0.70
     STATES
    0.70
    oult
    0.69
     Guer
    0.69
     Herman
    0.68
     Github
    0.66
     Directorate
    0.65
     HRC
    0.65
     Handling
    0.65
     chapter
    0.64
    Act Density 0.273%

    No Known Activations