© 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. 926
    Prev
    Next
    INDEX
    Explanations

    repeated references to specific groups or categories of people

    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
    staking
    -0.83
    gio
    -0.76
    lance
    -0.73
    rament
    -0.71
    hens
    -0.70
    enhagen
    -0.70
    mark
    -0.70
    nil
    -0.69
    gnu
    -0.69
    bour
    -0.68
    POSITIVE LOGITS
     footing
    0.76
     immune
    0.71
     headquartered
    0.70
     therape
    0.67
    izer
    0.66
     designed
    0.66
    elist
    0.65
     stationed
    0.65
     thrown
    0.64
     overseen
    0.63
    Activations Density 0.052%

    No Known Activations