© 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. 1418
    Prev
    Next
    INDEX
    Explanations

    phrases that express opinions about social justice issues

    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
    ��
    -0.90
    ァ
    -0.83
    hey
    -0.80
    iven
    -0.79
    must
    -0.79
    needs
    -0.78
    strength
    -0.76
    ��
    -0.74
    atur
    -0.73
    circle
    -0.73
    POSITIVE LOGITS
     evidence
    0.72
     presum
    0.72
     confirmation
    0.71
     evid
    0.71
     imagery
    0.70
     participation
    0.70
     revealing
    0.70
     insulting
    0.68
     news
    0.67
     casting
    0.67
    Activations Density 0.238%

    No Known Activations