Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 345
    Prev
    Next
    INDEX
    Explanations

    references to the term "consequences."

    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
     cones
    -0.71
    ahu
    -0.71
    ignt
    -0.71
     inspir
    -0.70
     references
    -0.70
    ascript
    -0.67
     tricks
    -0.66
     hints
    -0.66
     remembrance
    -0.65
     caves
    -0.64
    POSITIVE LOGITS
    .</
    0.79
     裏�
    0.75
    )</
    0.74
     Loan
    0.73
     MISS
    0.73
     Sloan
    0.71
     Related
    0.71
    �
    0.70
     Petr
    0.70
    20439
    0.70
    Activations Density 0.085%

    No Known Activations