[blovescoffee]

Instead of storing the correct answers in an encoded/embedded form in the weights of the neural net (certain neurons very loosely corresponding to certain "answers") the correct answers are stored elsewhere. That way we can scale down the model to the necessary "thinking" parts and we don't need to use excess neurons for the "memory" part. Kind of handwavey but hopefully that explains the general idea.

[kkjjkgjjgg]

You mean otherwise the whole words would be encoded in the net, and now you only need to encode the index in the database?