© 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. 1346
    Prev
    Next
    INDEX
    Explanations

    references to various forms of actions or acts, particularly those associated with violence or moral implications

    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
     hobbies
    -0.70
    eff
    -0.68
     intrusion
    -0.67
    acid
    -0.65
    aples
    -0.65
     Fighters
    -0.64
     Odyssey
    -0.64
    bones
    -0.64
     implants
    -0.63
     appointment
    -0.62
    POSITIVE LOGITS
    EngineDebug
    0.90
    uates
    0.80
    rica
    0.78
    onet
    0.77
    ilitary
    0.72
    imaru
    0.72
    iru
    0.72
    iable
    0.71
    icular
    0.71
    irie
    0.71
    Activations Density 0.038%

    No Known Activations