© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1183
    Prev
    Next
    INDEX
    Explanations

    statements or phrases involving consideration, comparison, 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
    stood
    -0.76
     flourish
    -0.74
     barely
    -0.73
     Directive
    -0.69
    none
    -0.68
     hardly
    -0.66
    sels
    -0.65
    SpaceEngineers
    -0.62
     scarcely
    -0.62
     nowhere
    -0.62
    POSITIVE LOGITS
     comparing
    0.73
     examining
    0.73
     analyzed
    0.71
     evaluated
    0.71
     examine
    0.69
     evaluate
    0.69
     calibrated
    0.68
    itness
    0.68
     examined
    0.67
     compare
    0.67
    Activations Density 0.148%

    No Known Activations