© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 2576
    Prev
    Next
    INDEX
    Explanations

    references to the appointment of special legal officials or counsel

    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
    arrow
    -0.71
    add
    -0.69
    ug
    -0.64
    girls
    -0.64
     skirts
    -0.64
    azer
    -0.63
    jp
    -0.63
    uren
    -0.63
    uben
    -0.63
    little
    -0.63
    POSITIVE LOGITS
    ICAN
    0.75
     Action
    0.71
     ACTION
    0.68
     Interstellar
    0.67
     medi
    0.66
     STATS
    0.66
     SOM
    0.66
     Warfare
    0.65
     CARE
    0.63
    estine
    0.63
    Activations Density 0.268%

    No Known Activations