INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     motion
    -2.84
    motion
    -2.55
     Motion
    -2.20
    Motion
    -2.09
     motions
    -2.03
     MOTION
    -1.97
     Motions
    -1.70
    motions
    -1.68
    MOTION
    -1.48
     beweging
    -1.15
    POSITIVE LOGITS
    ing
    1.12
    ally
    0.98
    alities
    0.82
    ed
    0.80
    ality
    0.77
    izing
    0.73
    ING
    0.69
    lessness
    0.69
    ising
    0.64
    iest
    0.63
    Act Density 0.387%

    No Known Activations