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. 97
    Prev
    Next
    INDEX
    Explanations

    references to problems or issues within a software or gaming 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
     leukemia
    -0.69
     pyramid
    -0.69
     discrep
    -0.65
    HEAD
    -0.64
     earthquake
    -0.62
     Madness
    -0.62
     earthquakes
    -0.61
     cough
    -0.61
    DEF
    -0.60
    selves
    -0.59
    POSITIVE LOGITS
    onte
    0.75
    EStreamFrame
    0.73
    anova
    0.69
    lain
    0.68
    quart
    0.68
    ides
    0.67
    esta
    0.67
    idates
    0.67
    adows
    0.65
     withd
    0.65
    Activations Density 0.139%

    No Known Activations