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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1663
    Prev
    Next
    INDEX
    Explanations

    phrases that express offense or inappropriate behavior

    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
    worthiness
    -0.67
    NOW
    -0.65
     Devi
    -0.62
     TTL
    -0.61
    now
    -0.61
    ital
    -0.60
    foot
    -0.60
     Freak
    -0.59
    Brow
    -0.59
     Anyway
    -0.56
    POSITIVE LOGITS
    oval
    0.83
     reflects
    0.76
    asin
    0.70
     predicted
    0.70
     announced
    0.69
     signaled
    0.65
    ocative
    0.65
    pires
    0.65
     suggested
    0.65
    undo
    0.64
    Activations Density 0.117%

    No Known Activations