Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Blog
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
GPT2-Small
6
3012
Prev
Next
MODEL
6
INDEX
Go
Explanations
words "refuting" or "refutes" or variations, word "supporting" and "backed up" especially when in regards to evidence, word "disprove"
Explanation Uploaded by User
No Scores
phrases about proving or disproving things by evidence or fact
Explanation Uploaded by User
No Scores
words and phrases related to evidence and verifying information.
oai_token-act-pair · gpt-4-turbo
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/6/3012?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/6/3012?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations