© 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. 1750
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases emphasizing speed and efficiency

    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
     gard
    -0.61
    noon
    -0.59
    cer
    -0.58
    hner
    -0.55
    ription
    -0.54
     gates
    -0.54
     Fell
    -0.54
     Riv
    -0.54
     Golf
    -0.54
     mo
    -0.54
    POSITIVE LOGITS
     WITHOUT
    0.94
     avoids
    0.84
    eva
    0.81
     toget
    0.80
     without
    0.79
     efficiently
    0.75
     anonymously
    0.74
     securely
    0.72
     succeed
    0.72
     withstand
    0.70
    Activations Density 0.244%

    No Known Activations