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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 580
    Prev
    Next
    INDEX
    Explanations

    repeated phrases indicating sources or references

    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
    SpaceEngineers
    -0.80
    Topic
    -0.70
    ウス
    -0.66
     RPGs
    -0.62
    Synopsis
    -0.62
    GW
    -0.61
    Reviewed
    -0.59
    Repe
    -0.59
    Accessory
    -0.59
    illion
    -0.58
    POSITIVE LOGITS
    itton
    0.68
    porter
    0.67
    ridges
    0.66
    ulia
    0.65
     withd
    0.65
    lev
    0.65
    hap
    0.64
    today
    0.62
    arent
    0.62
    elsius
    0.62
    Activations Density 0.030%

    No Known Activations