The current crop of AI weather models captures a surprisingly robust array of "core dynamics". E.g., recent work by Hakim and Masanam [1] reproduce classic dynamical core test cases on AI weather models and show that in many cases they robustly capture the expected dynamical responses to these highly idealized setups - setups far outside the bounds of what the models are trained on. What this means is that the causal or dynamical mechanisms producing a particular flow regime can very directly be inferred from the model.

[1]: https://journals.ametsoc.org/view/journals/aies/3/3/AIES-D-2...