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. 8-TRES-DC
    5. 165
    Prev
    Next
    INDEX
    Explanations

    references to tangible goods or resources

    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
    xon
    -0.90
    entin
    -0.77
    insky
    -0.70
    rams
    -0.70
    nces
    -0.69
    acket
    -0.68
    alach
    -0.68
    instein
    -0.67
    bats
    -0.66
    igious
    -0.66
    POSITIVE LOGITS
    istic
    0.78
    ize
    0.68
    istically
    0.68
    ocent
    0.68
    ista
    0.65
    izable
    0.65
    opolis
    0.63
    istas
    0.63
    opsy
    0.61
    ise
    0.61
    Activations Density 0.016%

    No Known Activations