Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 385
    Prev
    Next
    INDEX
    Explanations

    adjectives describing visual quality and complexity

    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
    thora
    -0.91
    uca
    -0.80
    hander
    -0.80
    daq
    -0.78
    epad
    -0.72
    ressor
    -0.70
    iggle
    -0.70
    urden
    -0.70
    iggurat
    -0.69
    pection
    -0.69
    POSITIVE LOGITS
     situations
    0.99
     resolutions
    0.97
     regimes
    0.92
     scenarios
    0.89
     propositions
    0.89
     protocols
    0.89
     workshops
    0.88
     demonstrations
    0.88
     percentages
    0.87
     interfaces
    0.87
    Activations Density 0.441%

    No Known Activations