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. 94
    Prev
    Next
    INDEX
    Explanations

    measurements of rates or frequencies

    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
    iculty
    -0.75
    recy
    -0.74
    izophren
    -0.73
    Requirements
    -0.70
    ivo
    -0.69
    alid
    -0.68
    pread
    -0.67
    atem
    -0.67
    une
    -0.67
    aves
    -0.67
    POSITIVE LOGITS
     hour
    0.85
     ann
    0.72
     cubic
    0.71
     burner
    0.66
     calendar
    0.66
     Nights
    0.66
     liner
    0.66
     watt
    0.64
     dram
    0.62
     minute
    0.62
    Activations Density 0.013%

    No Known Activations