INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     at
    -1.84
     Every
    -1.70
     During
    -1.69
     With
    -1.68
     Since
    -1.68
     Like
    -1.60
     As
    -1.58
     While
    -1.57
     after
    -1.55
     Even
    -1.53
    POSITIVE LOGITS
     faciliter
    1.63
     favoriser
    1.57
     mauva
    1.52
     oe
    1.51
     komfor
    1.45
     occuper
    1.43
     !!!!
    1.42
     laboratoire
    1.41
     kulinar
    1.41
     gewi
    1.38
    Act Density 0.063%

    No Known Activations