INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ibar
    -0.07
     Bern
    -0.06
     restau
    -0.06
     Fiona
    -0.06
    _Rect
    -0.06
    _ll
    -0.06
     ic
    -0.06
     cider
    -0.06
     Fi
    -0.06
     BB
    -0.06
    POSITIVE LOGITS
     maid
    0.07
    _environment
    0.06
    esting
    0.06
    -pressure
    0.06
     False
    0.06
     Βροχή
    0.06
     thickness
    0.06
    AR
    0.06
     Depths
    0.06
     mình
    0.06
    Act Density 0.018%

    No Known Activations