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. 253
    Prev
    Next
    INDEX
    Explanations

    references to different times of day, particularly related to "morning."

    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
    actionDate
    -0.86
    Must
    -0.73
     UCS
    -0.68
    FI
    -0.66
    20439
    -0.65
    -+-+
    -0.65
     Unch
    -0.64
    iPhone
    -0.64
    DAQ
    -0.64
     Tactical
    -0.62
    POSITIVE LOGITS
    hedon
    0.72
    inis
    0.71
    essional
    0.68
    owan
    0.65
    iety
    0.64
    otine
    0.64
    own
    0.63
     groceries
    0.63
     tears
    0.63
     hours
    0.62
    Activations Density 0.059%

    No Known Activations