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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 217
    Prev
    Next
    INDEX
    Explanations

     negative descriptors of leadership and governance

    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
    isSpecialOrderable
    -0.87
    holders
    -0.78
     Boxing
    -0.72
    resents
    -0.72
    Events
    -0.69
    ooks
    -0.68
    lear
    -0.68
    ={
    -0.68
    stones
    -0.67
    orld
    -0.67
    POSITIVE LOGITS
     counterproductive
    1.09
     unsustainable
    1.00
     ineffective
    0.97
     unsupported
    0.96
     unnecessary
    0.96
     wasteful
    0.94
     inaccurate
    0.94
     unconstitutional
    0.93
     costly
    0.92
     contradictory
    0.91
    Activations Density 0.137%

    No Known Activations