© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 432
    Prev
    Next
    INDEX
    Explanations

    key terms related to governance and foundational documents

    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
    Interstitial
    -0.81
    ��
    -0.75
    iHUD
    -0.67
     unbeliev
    -0.62
    Offline
    -0.62
    76561
    -0.60
    ��
    -0.59
    Compan
    -0.59
    EStream
    -0.59
    Cold
    -0.58
    POSITIVE LOGITS
     alone
    0.75
     contain
    0.72
    orah
    0.69
     save
    0.69
     spared
    0.68
    anos
    0.67
     accomplish
    0.66
    asta
    0.65
    itan
    0.64
     do
    0.64
    Activations Density 2.363%

    No Known Activations