Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 313
    Prev
    Next
    INDEX
    Explanations

    commands and suggestions related to consuming media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sunshine
    -0.60
     duck
    -0.59
     invitation
    -0.57
    water
    -0.55
    azing
    -0.54
     wishes
    -0.54
    iami
    -0.53
     wish
    -0.53
     moot
    -0.53
     blues
    -0.52
    POSITIVE LOGITS
     it
    0.88
    uve
    0.68
    anu
    0.65
    ().
    0.65
    itia
    0.64
    itted
    0.62
    orie
    0.62
    illac
    0.62
    !:
    0.61
     Patron
    0.60
    Activations Density 0.181%

    No Known Activations