© 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. 2329
    Prev
    Next
    INDEX
    Explanations

    phrases encouraging action and participation

    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
    poral
    -0.65
     clipping
    -0.65
     limb
    -0.63
    rament
    -0.63
     retaining
    -0.62
    hester
    -0.62
    oother
    -0.58
    pse
    -0.57
    unal
    -0.57
    quin
    -0.56
    POSITIVE LOGITS
     refuse
    0.91
     criticize
    0.85
     admit
    0.83
     ignore
    0.78
     pretend
    0.76
     argue
    0.75
     assume
    0.75
     accept
    0.74
     complain
    0.73
     reject
    0.72
    Activations Density 0.212%

    No Known Activations