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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1624
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing responsibility and accountability

    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
    eday
    -0.63
     Nora
    -0.63
    irement
    -0.61
    aterasu
    -0.60
     McCabe
    -0.60
    enne
    -0.59
    SOURCE
    -0.59
    atl
    -0.59
    oros
    -0.58
     McCull
    -0.58
    POSITIVE LOGITS
    ══
    0.73
    ト
    0.73
    ById
    0.73
     arbitrary
    0.67
     unsu
    0.65
     intolerance
    0.64
     insult
    0.63
     arbitrarily
    0.63
     exaggerated
    0.62
    LOCK
    0.62
    Activations Density 1.587%

    No Known Activations