Fascinating visualization. To think, we can visualize the entire* process but cannot understand the inner workings of a model with regards to decision making. This was true last I looked into it a year or so ago, not aware on any advancements in that aspect.
We completely understand the inner workings and can see the emerging result, but it's hard for us to accept that it took no decision and just chose a nice word to complete a sentence, time after time, and sounds intelligent. Then it says Strawberry has two r, and you're like ok, it's just a huge statistical matrix with zero value.
Hammers have zero value when you’re trying to cook food with them, too.