9
		LLM Task Underspecification Detection
👀
Evaluate gendered pronoun resolution in text
Visualize transformer computations with a tuned lens
Interact with Falcon-Chat for personalized conversations
Track, rank and evaluate open LLMs and chatbots
Generate color-coded text based on token probabilities
Explore and calibrate model predictions to better understand probabilities
Generate text answers to various prompts
Generate code snippets in Python, Java, JavaScript