Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 9-TRES-DC
    5. 664
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases addressing the reader directly

    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
    brow
    -0.86
    ochet
    -0.76
    asionally
    -0.74
    urst
    -0.72
    olkien
    -0.72
    iggins
    -0.72
    izzle
    -0.71
    iasis
    -0.71
    agonist
    -0.70
    athering
    -0.70
    POSITIVE LOGITS
     insign
    0.73
    Safe
    0.67
     Vil
    0.65
     Pwr
    0.64
     Username
    0.63
    Proof
    0.62
     Pere
    0.62
     Proof
    0.61
    icidal
    0.61
     Lithuania
    0.61
    Activations Density 0.029%

    No Known Activations