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. 355
    Prev
    Next
    INDEX
    Explanations

    semicolons used in citations or bibliographies

    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
    ~~~~
    -0.70
    externalActionCode
    -0.69
    Whereas
    -0.65
    MR
    -0.65
     altogether
    -0.65
    };
    -0.65
    mobi
    -0.64
    ~~~~~~~~
    -0.62
    mill
    -0.62
    ;
    -0.61
    POSITIVE LOGITS
     pione
    1.05
    yrinth
    0.79
     newcom
    0.78
    aditional
    0.78
     externalTo
    0.77
    �
    0.76
    
    0.76
     subur
    0.75
    
    0.75
    
    0.75
    Activations Density 0.076%

    No Known Activations