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. 260
    Prev
    Next
    INDEX
    Explanations

    symbols or non-typical characters

    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
    uum
    -0.70
    ドラ
    -0.69
    ruck
    -0.66
    mouth
    -0.65
    yon
    -0.65
    emed
    -0.65
    izen
    -0.64
    �
    -0.63
    erd
    -0.63
    agascar
    -0.62
    POSITIVE LOGITS
     culminating
    0.96
     concluding
    0.83
     overriding
    0.77
     compr
    0.77
     leading
    0.77
     granting
    0.75
     resulting
    0.75
     allowing
    0.74
     defining
    0.73
     succeeding
    0.71
    Activations Density 0.108%

    No Known Activations