© 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. 480
    Prev
    Next
    INDEX
    Explanations

    references to individuals' current and former roles or statuses

    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
    CEPT
    -0.66
     feedback
    -0.64
     unintended
    -0.63
    apt
    -0.62
     reaction
    -0.62
     instincts
    -0.60
     insights
    -0.59
     insight
    -0.58
    Trade
    -0.58
     encouraging
    -0.57
    POSITIVE LOGITS
    ��
    0.80
    renheit
    0.78
    aneers
    0.73
    stood
    0.70
    heit
    0.65
    umbn
    0.63
     Ply
    0.63
    ainment
    0.62
    chwitz
    0.61
     Dunham
    0.61
    Activations Density 0.193%

    No Known Activations