Earlier quoted context omitted.
There's both. With the web interface it clearly has stopwords or similar. If you run it locally and ask about e.g. Tienanmen square, the cultural revolution or Winnie-the-Pooh in China, it gives a canned response to talk about something else, with an empty CoT. But usually if you just ask the question again it starts to output things in the CoT, often with something like "I have to be very sensitive about this subjec…
This is super interesting. I am not an expert on the training: can you clarify how/when the censorship is "baked" in? Like is the a human supervised dataset and there is a reward for the model conforming to these censored answers?
You could do it in different ways, but if you're using synthetic data then you can pick and choose what kind of data you generate which is then used to train these models; that's a way of baking in the censorship.