What is Referrer-Policy useful for?
PICTURE THIS: A SENTENCE BECOMES TOKENS
The model does not read letters like humans. It reads these pieces, then predicts the next one.
Simple meaning
It limits URL leakage in Referer headers.
WHY — Security instead of guessing?
Why interviewers care about Security:
who only read docs from people who shipped.
and tied to .NET MVC work.
Name the idea, why it exists, then one short example.
End with when you use it and one common pitfall.
STEPS — What happens with tokens?
Before the model can read a sentence, it goes through these steps:
- 1It limits URL leakage
in Referer headers.
- 2Token IDs
Strict-origin-when-cross-origin is a common default.
- 3Auth tokens must never
sit in query strings.
- 4Context mix
Attention looks at nearby tokens together.
- 5Next token
The model scores what should come next.
- 6Decode
IDs turn back into readable text.
EXAMPLE — See it in action
Let's see how a real sentence is tokenized (tokens may vary by model):
Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).
Key takeaway
It limits URL leakage in Referer headers. Strict-origin-when-cross-origin is a common default.