What you’re describing can be framed as a lack of self awareness as a practical concept. You know whether you know something or not. It, conversely, maps stimuli to a vector. It can’t not do that. It cannot decide that it hasn’t „seen” such stimuli in its training. Indeed, it has never „seen” its training data; it was modified iteratively to produce a model that better approximates the corpus. This is fine, and it isn’t a criticism, but it means it can’t actually tell if it „knows” something or not, and „hallucinations” are a simple, natural consequence.