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. 290
    Prev
    Next
    INDEX
    Explanations

    sentences that contain a significant conclusion or observation

    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
     ingred
    -0.78
     chain
    -0.76
     projecting
    -0.71
     guid
    -0.71
     juggling
    -0.71
     prosec
    -0.70
     merging
    -0.68
     scaff
    -0.68
     desired
    -0.68
     combinations
    -0.67
    POSITIVE LOGITS
     Consider
    0.88
     During
    0.88
     Whilst
    0.84
     Throughout
    0.83
     Suppose
    0.83
     Once
    0.81
     While
    0.81
     Everyone
    0.81
     Whenever
    0.80
     Almost
    0.80
    Activations Density 0.322%

    No Known Activations