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. 324
    Prev
    Next
    INDEX
    Explanations

    questions posed in the text

    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
    hya
    -0.70
    bably
    -0.67
    OUND
    -0.67
    paio
    -0.64
    Statistics
    -0.61
    iful
    -0.59
    hematically
    -0.59
    undai
    -0.59
     effects
    -0.58
     outcomes
    -0.58
    POSITIVE LOGITS
    asks
    0.78
     asks
    0.65
     asked
    0.65
     inquired
    0.62
    asking
    0.62
     pond
    0.61
     quer
    0.59
     Bought
    0.58
     apologise
    0.58
    Quest
    0.57
    Activations Density 0.018%

    No Known Activations