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. 617
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of independence or self-identity

    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
     renewable
    -0.77
    Offline
    -0.67
    aer
    -0.66
     renewables
    -0.64
    ero
    -0.63
    externalActionCode
    -0.61
    oother
    -0.61
    Chain
    -0.60
    atform
    -0.60
    eatures
    -0.60
    POSITIVE LOGITS
     caricature
    0.76
     pigeon
    0.75
     behold
    0.74
     clam
    0.73
    poons
    0.70
     insin
    0.69
    poon
    0.68
    agons
    0.67
     insults
    0.65
     preach
    0.64
    Activations Density 0.223%

    No Known Activations