© 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. 1110
    Prev
    Next
    INDEX
    Explanations

    the word "Anyone" and its variations, indicating a focus on inclusivity or addressing the audience

    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
    方
    -0.69
     dusk
    -0.64
    peace
    -0.63
    esis
    -0.63
    ¨
    -0.62
     Reincarn
    -0.62
     Conquest
    -0.61
    asted
    -0.61
     stabilization
    -0.61
    oing
    -0.61
    POSITIVE LOGITS
     who
    0.71
    aunts
    0.71
     encount
    0.69
    ANY
    0.69
    idents
    0.69
    ettings
    0.69
     cares
    0.68
     impatient
    0.68
     acquainted
    0.67
    who
    0.66
    Activations Density 0.025%

    No Known Activations