© 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. 1406
    Prev
    Next
    INDEX
    Explanations

    references to systems and structures that are designed or proposed to function effectively

    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
    -0.73
    Cra
    -0.71
    */(
    -0.69
    ---------
    -0.69
    HT
    -0.68
     Childhood
    -0.66
    xia
    -0.65
    ��
    -0.65
    former
    -0.65
    ��
    -0.65
    POSITIVE LOGITS
     maxim
    0.90
     understands
    0.88
     integrates
    0.86
     conform
    0.82
     allows
    0.81
     protects
    0.80
     satisfies
    0.79
     accepts
    0.79
     absorbs
    0.79
     balances
    0.78
    Activations Density 0.146%

    No Known Activations