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. 269
    Prev
    Next
    INDEX
    Explanations

    themes of nobility and peacefulness in actions or situations

    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
    enegger
    -0.88
    uble
    -0.87
    idate
    -0.80
    iman
    -0.78
    tex
    -0.78
    ̶
    -0.75
    illet
    -0.74
    itable
    -0.73
    aki
    -0.73
    ctors
    -0.73
    POSITIVE LOGITS
     intentions
    0.89
     aspirations
    0.86
     displeasure
    0.79
     objections
    0.77
     feelings
    0.75
     objection
    0.75
     desires
    0.74
     thoughts
    0.73
     concerns
    0.72
    folk
    0.71
    Activations Density 0.111%

    No Known Activations