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. 233
    Prev
    Next
    INDEX
    Explanations

    terms related to restriction or reduction

    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
    rup
    -0.70
    SourceFile
    -0.69
    Done
    -0.66
    grave
    -0.66
    bill
    -0.65
    ANK
    -0.64
    pty
    -0.64
    ��
    -0.64
    kson
    -0.63
    ifferent
    -0.62
    POSITIVE LOGITS
     functionality
    0.74
     visibility
    0.73
     boundaries
    0.70
     influence
    0.67
     prominence
    0.67
     capabilities
    0.66
     opportunities
    0.65
     importance
    0.65
     participation
    0.64
     recovery
    0.63
    Activations Density 0.117%

    No Known Activations