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. 285
    Prev
    Next
    INDEX
    Explanations

    connections or associations between different concepts or entities

    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
     multiplying
    -0.64
     offending
    -0.58
    furt
    -0.57
    wered
    -0.57
     deviation
    -0.55
    Reviewer
    -0.55
    assault
    -0.55
     disbel
    -0.55
    iard
    -0.54
     Sins
    -0.54
    POSITIVE LOGITS
     to
    0.78
     thereto
    0.74
    azy
    0.73
    qqa
    0.68
    egg
    0.65
    ibaba
    0.64
    ña
    0.61
    zona
    0.60
     nominate
    0.59
    inas
    0.59
    Activations Density 0.173%

    No Known Activations