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. 79
    Prev
    Next
    INDEX
    Explanations

    statistics or percentages related to demographic groups

    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
    ADRA
    -0.85
    MAL
    -0.66
     Koch
    -0.64
     unden
    -0.63
     testament
    -0.63
     nodd
    -0.63
    azel
    -0.61
     Lazarus
    -0.60
    IGHT
    -0.60
    ELF
    -0.60
    POSITIVE LOGITS
    %,
    0.70
     points
    0.70
     percent
    0.68
     cents
    0.67
    %
    0.64
     pts
    0.62
     percentile
    0.62
     penetration
    0.62
    º
    0.62
     versus
    0.61
    Activations Density 0.076%

    No Known Activations