INDEX
    Explanations

    verbs related to expressing intentions or desires

    expressions of desire or intention

    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.72
    glers
    -0.71
     Juven
    -0.66
    ikhail
    -0.65
     itself
    -0.61
    their
    -0.61
    Eva
    -0.60
    eers
    -0.60
     alike
    -0.59
     Pse
    -0.58
    POSITIVE LOGITS
     personally
    1.07
    poke
    0.79
     resign
    0.74
     "#
    0.72
     constituents
    0.72
    realDonaldTrump
    0.68
    otom
    0.67
    oan
    0.67
    olit
    0.65
    76561
    0.65
    Act Density 0.551%

    No Known Activations