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. 349
    Prev
    Next
    INDEX
    Explanations

    references to specific religions and their practices

    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
    conom
    -0.74
     Kamp
    -0.63
    aer
    -0.62
    chwitz
    -0.59
    owitz
    -0.59
    witz
    -0.59
     Armenia
    -0.58
    manship
    -0.58
    rity
    -0.58
    セ
    -0.57
    POSITIVE LOGITS
    ulations
    0.59
    existing
    0.59
     encountering
    0.55
     silenced
    0.55
    >>
    0.54
     loudly
    0.54
     implemented
    0.54
    ":["
    0.53
     viol
    0.53
     continue
    0.53
    Activations Density 0.217%

    No Known Activations