INDEX
    Explanations

    describing actions or qualities

    New Auto-Interp
    Negative Logits
     zunehm
    0.91
     Cous
    0.85
     wiederum
    0.85
    šću
    0.83
    ksiyon
    0.83
    ümüzde
    0.83
    0.81
    Lookup
    0.81
    Oh
    0.81
    返品
    0.81
    POSITIVE LOGITS
     hand
    1.13
     scratch
    0.84
     brush
    0.82
    hand
    0.80
     difficulty
    0.79
     bl
    0.77
     effort
    0.77
     second
    0.73
     blo
    0.73
     precision
    0.71
    Act Density 0.000%

    No Known Activations