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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 178
    Prev
    Next
    INDEX
    Explanations

    concepts related to respect and adherence to human rights

    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
    arma
    -0.77
    osta
    -0.77
    onse
    -0.74
    eele
    -0.74
    ktop
    -0.74
    raq
    -0.73
    role
    -0.73
    hedon
    -0.73
    NetMessage
    -0.73
    ł
    -0.72
    POSITIVE LOGITS
     peoples
    0.70
     indigenous
    0.68
     Cth
    0.68
     traditions
    0.68
     contestants
    0.66
     tradition
    0.65
     victims
    0.65
     pree
    0.65
     sovereign
    0.64
     yours
    0.64
    Activations Density 0.108%

    No Known Activations