© 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. 1353
    Prev
    Next
    INDEX
    Explanations

    references to unlawful or harsh treatment of individuals

    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
     Corpus
    -0.67
    Perfect
    -0.66
    bern
    -0.66
     fallacy
    -0.65
    agree
    -0.64
    behind
    -0.64
     Leth
    -0.62
    pose
    -0.62
     Fail
    -0.61
     Lose
    -0.61
    POSITIVE LOGITS
     treated
    1.07
     teased
    1.03
     punished
    0.98
     discriminated
    0.94
     subjected
    0.94
     bullied
    0.94
     singled
    0.94
     interrogated
    0.91
     rewarded
    0.90
     ridiculed
    0.90
    Activations Density 1.688%

    No Known Activations