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. 9-TRES-DC
    5. 672
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating the end of sentences

    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
     tremend
    -0.93
     entitle
    -0.78
     carbohyd
    -0.76
    alore
    -0.76
     referen
    -0.76
    ratulations
    -0.75
    uron
    -0.75
     hesitate
    -0.74
    uckland
    -0.74
    atem
    -0.73
    POSITIVE LOGITS
     Continued
    0.94
     Journals
    0.89
     Pets
    0.86
     Camer
    0.85
     Shoes
    0.85
     Strategies
    0.85
     Traps
    0.84
     Pigs
    0.84
     Ending
    0.83
     Chains
    0.83
    Activations Density 0.484%

    No Known Activations