Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
sebzim4500
on May 9, 2023
|
parent
|
context
|
favorite
| on:
Language models can explain neurons in language mo...
Yeah, that's where they apply the activation function and that happens per neuron so you can't rotate everything and expect the same result.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: