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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 731
    Prev
    Next
    INDEX
    Explanations

    references to governmental accountability and actions

    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
     diving
    -0.69
     proper
    -0.68
    emouth
    -0.67
     Referred
    -0.62
     discriminating
    -0.61
     competent
    -0.59
    due
    -0.58
    Results
    -0.58
     abusing
    -0.57
     intervening
    -0.57
    POSITIVE LOGITS
    anza
    0.74
    aples
    0.74
    vice
    0.72
    cca
    0.70
     Fukushima
    0.69
    elta
    0.68
    terness
    0.68
    olls
    0.64
    auldron
    0.64
    aban
    0.63
    Activations Density 0.384%

    No Known Activations