INDEX
    Explanations

    mentions of the name "Rick."

    New Auto-Interp
    Negative Logits
    iral
    -0.15
    _UD
    -0.15
    ignum
    -0.14
    hatt
    -0.14
    奴
    -0.14
     affairs
    -0.14
    arith
    -0.14
     báºŃc
    -0.13
    -strokes
    -0.13
    indow
    -0.13
    POSITIVE LOGITS
    ards
    0.26
    ard
    0.20
    ardo
    0.19
    shaw
    0.19
    ety
    0.18
    roll
    0.17
    ARDS
    0.16
    arton
    0.15
    engo
    0.15
    rolled
    0.15
    Act Density 0.007%

    No Known Activations