© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 552
    Prev
    Next
    INDEX
    Explanations

    instances of the word "choice" in various contexts

    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
    \\\\\\\\
    -0.88
    Pocket
    -0.76
    ware
    -0.65
     flee
    -0.65
     convenience
    -0.63
     Carbuncle
    -0.62
     blanket
    -0.61
    Ire
    -0.59
    winner
    -0.59
    Desk
    -0.58
    POSITIVE LOGITS
    inery
    0.73
    ertation
    0.72
    iger
    0.70
    emen
    0.68
    yss
    0.67
    aci
    0.65
    iosis
    0.64
    aptic
    0.64
    adian
    0.63
    endi
    0.63
    Activations Density 0.042%

    No Known Activations