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. 333
    Prev
    Next
    INDEX
    Explanations

    the term "great" in various contexts

    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
    ¯¯¯¯¯¯¯¯
    -0.66
    RAG
    -0.63
    カ
    -0.62
    �
    -0.60
    urat
    -0.60
    chenko
    -0.59
     Cub
    -0.58
    sure
    -0.58
    aterial
    -0.57
     Kry
    -0.57
    POSITIVE LOGITS
    anwhile
    0.89
    theless
    0.73
    abouts
    0.68
    icides
    0.65
    stores
    0.65
    arth
    0.63
    drivers
    0.63
    street
    0.62
    venient
    0.61
    erity
    0.61
    Activations Density 0.069%

    No Known Activations