© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1349
    Prev
    Next
    INDEX
    Explanations

    references to the general population or groups of people

    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
    黒
    -0.73
    BuyableInstoreAndOnline
    -0.67
     similarities
    -0.67
     Dynasty
    -0.65
    failed
    -0.62
     hinges
    -0.61
     flashbacks
    -0.61
     preced
    -0.60
     circumstances
    -0.60
    CHAT
    -0.60
    POSITIVE LOGITS
    urally
    0.80
    clud
    0.74
    imming
    0.73
    hirt
    0.67
     lining
    0.66
    ims
    0.65
    ically
    0.65
    ila
    0.65
    iling
    0.63
    asta
    0.63
    Activations Density 0.219%

    No Known Activations