[spion]

Try this prompt:

    For the following question, do all the calculations first and write them out. Only then answer the question based strictly on the result of the calculations. 
    
    What is heavier, 1000 tons of helium or a cubic meter of osmium?

Otherwise, you get a high-probability answer guided by the training data (which contains a lot of trick questions) and a bunch of attempts of the LLM to justify the wrong answer.