INDEX
    Explanations

    words related to washing or cleanliness

    occurrences of the word "wash" and its variations

    New Auto-Interp
    Negative Logits
    reme
    -0.77
    vernment
    -0.75
    iasm
    -0.75
    rious
    -0.70
    */(
    -0.69
     rul
    -0.65
    CVE
    -0.65
    ourke
    -0.64
     reluct
    -0.64
    yrinth
    -0.63
    POSITIVE LOGITS
     ashore
    1.18
    cloth
    1.04
    rooms
    0.95
    stakes
    0.92
    robe
    0.91
    aways
    0.88
    houses
    0.87
    tons
    0.84
    down
    0.82
    room
    0.79
    Act Density 0.018%

    No Known Activations