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. 286
    Prev
    Next
    INDEX
    Explanations

    instances of the word "same."

    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
    netflix
    -0.80
    イト
    -0.79
    ール
    -0.79
    perty
    -0.78
    bowl
    -0.78
    nesday
    -0.77
    amar
    -0.74
    Same
    -0.74
    TPPStreamerBot
    -0.73
    uyomi
    -0.73
    POSITIVE LOGITS
     wreck
    0.77
     Universe
    0.70
    taboola
    0.69
     civilisation
    0.68
     world
    0.66
    ussie
    0.66
     occupant
    0.65
     mom
    0.65
     hi
    0.65
     aut
    0.64
    Activations Density 0.023%

    No Known Activations