INDEX
    Explanations

    references to natural resources and mining activities, particularly gold and gas

    New Auto-Interp
    Negative Logits
     pacman
    -0.14
     dav
    -0.13
     Glyph
    -0.13
    xB
    -0.13
     anonym
    -0.13
     censor
    -0.13
    olver
    -0.13
    à¥įमà¤ķ
    -0.13
    unci
    -0.13
     refl
    -0.12
    POSITIVE LOGITS
     deposits
    0.42
     deposit
    0.35
     reserves
    0.34
     Depos
    0.33
     Deposit
    0.28
    deposit
    0.28
     extraction
    0.27
    Deposit
    0.27
     Extraction
    0.25
     extracting
    0.24
    Act Density 0.170%

    No Known Activations