© 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. 1069
    Prev
    Next
    INDEX
    Explanations

    the word "instead" and its variations, emphasizing contrasts or alternatives

    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
    vation
    -0.81
    Status
    -0.68
    ◼
    -0.66
    licted
    -0.66
    nostic
    -0.66
    answer
    -0.64
    gerald
    -0.63
    mor
    -0.62
    mot
    -0.62
    />
    -0.62
    POSITIVE LOGITS
    forth
    0.69
     we
    0.68
     they
    0.66
     Bohem
    0.66
    ihara
    0.65
     of
    0.63
    of
    0.63
     OF
    0.62
    ','
    0.59
    itiz
    0.59
    Activations Density 0.015%

    No Known Activations