3-21+G and 3-21+G* in Gaussian



 Hallo Netters,
      I discovered, somewhat to my surprise, that the basis sets 3-21+G
 and 3-21+G* give different energies for fully optimized geometries..
 (Yes, my molecules ONLY contain atoms through Fluorine).. I thought
 just adding diffuse functions did not change the 3-21G = 3-21G* relationship.
 Boy, was I wrong. A hundred kcals wrong! Can anybody point out what
 I am missing???????
 Thanks.
 J. Weston
 --------
 ge91' at \`maier.org.chemie.uni-giessen.de