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. 29
    Prev
    Next
    INDEX
    Explanations

    mentions of characters and specific names within the narrative

    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
     Ug
    -0.62
     Barbarian
    -0.62
     Protoss
    -0.60
     Advisor
    -0.59
     Rabbi
    -0.58
     Founding
    -0.58
     Jenn
    -0.58
     Shards
    -0.57
     Talking
    -0.57
     Palestinian
    -0.56
    POSITIVE LOGITS
    aline
    0.87
    ctuary
    0.79
    let
    0.75
    iard
    0.72
    lets
    0.69
    xual
    0.68
     wisely
    0.66
    ′
    0.66
    hyde
    0.65
    mega
    0.65
    Activations Density 0.333%

    No Known Activations