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. 84
    Prev
    Next
    INDEX
    Explanations

    statistical estimates or approximations in numerical context

    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
    tools
    -0.75
     pronouns
    -0.61
    uum
    -0.61
     interviews
    -0.60
    itol
    -0.59
    Studio
    -0.59
    GU
    -0.58
     separates
    -0.57
    ::::::::
    -0.56
    Secure
    -0.56
    POSITIVE LOGITS
    -)
    0.73
     Mae
    0.73
    oday
    0.68
    soDeliveryDate
    0.65
    blogspot
    0.64
    ering
    0.63
    etting
    0.63
     5000
    0.63
    ijn
    0.62
     doubling
    0.62
    Activations Density 0.020%

    No Known Activations