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. 152
    Prev
    Next
    INDEX
    Explanations

    questions or phrases that inquire about types or categories of things

    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
    ATIONS
    -0.69
    uble
    -0.67
    EF
    -0.65
    ELL
    -0.65
     Ess
    -0.61
     Drift
    -0.59
     Et
    -0.57
    itations
    -0.57
     THREE
    -0.57
     Prelude
    -0.55
    POSITIVE LOGITS
    of
    0.98
     of
    0.93
    luster
    0.80
    nesses
    0.72
    achu
    0.69
    icles
    0.68
     thereof
    0.67
     OF
    0.64
     Of
    0.64
    oft
    0.64
    Activations Density 0.032%

    No Known Activations