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. 140
    Prev
    Next
    INDEX
    Explanations

    references to global news and media

    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
    cipl
    -0.72
    RESULTS
    -0.69
     surviving
    -0.66
     fullest
    -0.64
    ensed
    -0.64
    uous
    -0.64
    ENDED
    -0.62
     endings
    -0.61
    SOURCE
    -0.60
    imates
    -0.60
    POSITIVE LOGITS
     Opera
    0.69
     Liberty
    0.64
     opera
    0.63
     Utilities
    0.62
     Defeat
    0.61
     Missile
    0.60
     Joined
    0.59
     resembling
    0.59
     CONTROL
    0.59
     Audit
    0.58
    Activations Density 0.009%

    No Known Activations