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. 9-TRES-DC
    5. 665
    Prev
    Next
    INDEX
    Explanations

    references to the number of bedrooms in residential properties

    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
     mint
    -0.62
     clipboard
    -0.60
    ream
    -0.59
     laun
    -0.58
    ensis
    -0.58
     wa
    -0.57
     obscurity
    -0.55
     Pupp
    -0.55
     anten
    -0.55
     constitu
    -0.53
    POSITIVE LOGITS
    story
    1.00
    bedroom
    0.86
    floor
    0.83
     acre
    0.83
    acre
    0.83
    oyer
    0.77
    osion
    0.74
    plex
    0.74
     hect
    0.70
     STORY
    0.69
    Activations Density 0.157%

    No Known Activations