INDEX
    Explanations

    expressions of desire or intention regarding actions and goals

    New Auto-Interp
    Negative Logits
    egli
    -0.43
     unsuccessful
    -0.37
     Groves
    -0.37
     anh
    -0.36
     technique
    -0.35
    fiche
    -0.35
     Pyle
    -0.35
     infamous
    -0.35
     ingenious
    -0.35
     DD
    -0.34
    POSITIVE LOGITS
     want
    1.30
    want
    1.26
     WANT
    1.22
     Want
    1.21
    Want
    1.16
    wants
    1.13
     wants
    1.07
     Wants
    1.07
    WANT
    1.02
     wanting
    0.97
    Act Density 0.181%

    No Known Activations