Transferability depends on the way the models is set up, and moves on a scale.
Introspectable: given that you can ask unlimited "What if" questions models, we should be able to get a lot of insights into how the models work internally. And you can often design them to be introspectable as some performance or complexity cost. (if that's what you meant by introspectable).
Introspectable: given that you can ask unlimited "What if" questions models, we should be able to get a lot of insights into how the models work internally. And you can often design them to be introspectable as some performance or complexity cost. (if that's what you meant by introspectable).