© 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. 1049
    Prev
    Next
    INDEX
    Explanations

    references to the title "Prime Minister."

    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
     inception
    -0.67
     interception
    -0.66
     isot
    -0.65
     possess
    -0.63
    aundering
    -0.62
    opter
    -0.61
    fters
    -0.60
    uyomi
    -0.60
     actu
    -0.59
     estimation
    -0.58
    POSITIVE LOGITS
    ngth
    0.70
    ummer
    0.69
    dor
    0.67
    ayed
    0.65
    our
    0.64
    beard
    0.63
     Sebast
    0.63
    haw
    0.61
     Uri
    0.61
     Reed
    0.60
    Activations Density 0.024%

    No Known Activations