Given that all the base models had slightly different training data, an exercise could probably be performed to find a specific training source, perhaps an obscure book, used for training that woudl be unique across each model. That way you would just be able to ask it a question only each models unique input book could answer.
There’s gotta be a way to fingerprint the output though. Like some kind of shibboleth that gives the model away based on how it responds?
Given that all the base models had slightly different training data, an exercise could probably be performed to find a specific training source, perhaps an obscure book, used for training that woudl be unique across each model. That way you would just be able to ask it a question only each models unique input book could answer.