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. 254
    Prev
    Next
    INDEX
    Explanations

    references to the concept of population or the number of people involved 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
    CVE
    -0.70
    projects
    -0.69
    ウス
    -0.68
    �
    -0.68
    �
    -0.67
     blat
    -0.66
    �
    -0.65
    groups
    -0.65
    DonaldTrump
    -0.65
    く
    -0.65
    POSITIVE LOGITS
     obtained
    0.77
     admitted
    0.74
     married
    0.73
     signed
    0.71
     enrolled
    0.70
     subject
    0.70
     served
    0.70
     Investig
    0.70
     entered
    0.69
     exempted
    0.68
    Activations Density 0.390%

    No Known Activations