# How to decrease False Positive RASA 2.8.6

**URL:** <https://forum.rasa.com/t/how-to-decrease-false-positive-rasa-2-8-6/48510>\
**Category:** Rasa Open Source\
**Created:** [October 15, 2021, 12:27pm UTC](https://forum.rasa.com/t/how-to-decrease-false-positive-rasa-2-8-6/48510 "2021-10-15T12:27:49Z")\
**Posts on this page:** 1\
**Showing post:** 7

<div class="post-metadata">

**Author:** ![rctatman](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/rctatman/32/6734_2.png) [@rctatman](https://forum.rasa.com/u/rctatman)\
**Post date:** [October 26, 2021, 8:59pm UTC](https://forum.rasa.com/t/how-to-decrease-false-positive-rasa-2-8-6/48510/7 "2021-10-26T20:59:47Z")

</div>

I believe that’s expected behaviour; tokens oov for another model can still be learned/given weights by the countVectorsFeaturizer: [spaCy and OOV-Tokens](http://forum.rasa.com/t/spacy-and-oov-tokens/31762)

The high confidence is probably due to specific tokens being strongly associated with specific intents.

---

_[View the full topic](https://forum.rasa.com/t/how-to-decrease-false-positive-rasa-2-8-6/48510)._