Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Contribute
Light
Dark
Antonym Dataset (Nguyen et al. 2017)
Report a problem with this record
anchor
Findings
IC-744
The decoded vocabulary of a function vector often reflects the task's output space, but reconstructing a vector that matches this vocabulary distribution does not recover the FV's full causal effect.
[eval]