fix: Set shareimg for Patching explorable.

Author: jimbojw

source/_posts/2024-02-28-patching.md

@@ -2,7 +2,7 @@
 template: post_v2.html
 title: Can Large Language Models Explain Their Internal Mechanisms?
 socialsummary: An interactive introduction to Patchscopes, an inspection framework for explaining the hidden representations of large language models, with large language models.
-shareimg: TKTK
+shareimg: https://pair.withgoogle.com/explorables/images/patching-up-close.png
 shareimgabstract:
 authors: Nada Hussein<a class='footstart small' key=author></a>, Asma Ghandeharioun<a class='footstart small' key=author></a>, Ryan Mullins, Emily Reif, Jimbo Wilson, Nithum Thain<a class='footstart small' key=author2></a>, Lucas Dixon<a class='footstart small' key=author2></a>
 date: July 2024