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. 64
    Prev
    Next
    INDEX
    Explanations

    references to primary and secondary classifications

    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
    classic
    -0.82
    quet
    -0.79
    generic
    -0.76
    ��極
    -0.73
     Cosponsors
    -0.72
    Smart
    -0.72
     Reloaded
    -0.71
    fitting
    -0.71
     Annotations
    -0.71
    Anonymous
    -0.70
    POSITIVE LOGITS
     residence
    0.83
     concern
    0.71
     careg
    0.67
     focus
    0.67
     jurisdiction
    0.66
     custody
    0.66
     care
    0.64
     purpose
    0.64
     headquarters
    0.63
     marker
    0.63
    Activations Density 0.044%

    No Known Activations