© 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. 2708
    Prev
    Next
    INDEX
    Explanations

    sentences that convey advice or suggestions

    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
     anx
    -0.81
     suspic
    -0.78
     urgently
    -0.75
     thirst
    -0.72
     further
    -0.70
    thinkable
    -0.69
     desires
    -0.68
     preferred
    -0.67
     wish
    -0.66
     predetermined
    -0.66
    POSITIVE LOGITS
     Explain
    0.92
     Because
    0.91
     Ignore
    0.82
     Nobody
    0.82
     Fail
    0.79
     Sometimes
    0.78
     Customers
    0.78
     Buy
    0.78
     Expend
    0.77
     You
    0.76
    Activations Density 0.312%

    No Known Activations