© 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. 1553
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "l" and related phrases indicating requests or permissions

    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
     Archdemon
    -0.85
    emate
    -0.78
    alse
    -0.73
    anguage
    -0.72
    nces
    -0.71
    arcity
    -0.70
    aneers
    -0.70
    覚醒
    -0.69
    abase
    -0.66
    risis
    -0.65
    POSITIVE LOGITS
     entry
    0.81
     permission
    0.78
     forgiveness
    0.72
     input
    0.71
     Entry
    0.71
     Info
    0.70
    Entry
    0.69
     access
    0.68
     entered
    0.67
     divul
    0.67
    Activations Density 1.363%

    No Known Activations