Update app.py

app.py

@@ -113,6 +113,8 @@ with GraInter:
     **UGI: Uncensored General Intelligence**. A measurement of the amount of uncensored/controversial information an LLM knows about. It is calculated from the average score of 5 subjects LLMs commonly refuse to talk about. The leaderboard is made of roughly 60 questions/tasks, measuring both "willingness to answer" and "accuracy" in controversial fact-based questions. I'm choosing to keep the questions private so people can't train on them and devalue the leaderboard.
     
     **W/10:** A more narrow, 10-point score, solely measuring the LLM's Willingness to answer the most controversial questions.
+
+    A high UGI but low W/10 could mean for example that the model can provide a lot of sensitive information, but will refuse to form the information into a malicious argument.
     
     **Unruly:** Knowledge of activities that are generally frowned upon.