© 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. 1943
    Prev
    Next
    INDEX
    Explanations

    references to varying levels or degrees of something

    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
    ETS
    -0.79
    quished
    -0.78
    NPR
    -0.78
    LIST
    -0.75
    eters
    -0.73
    isites
    -0.72
     Newly
    -0.72
    uries
    -0.72
    urous
    -0.71
    eeper
    -0.71
    POSITIVE LOGITS
     abstraction
    0.80
     inhibition
    0.79
     autonomy
    0.77
     derog
    0.71
     nuance
    0.69
     unanim
    0.68
     redundancy
    0.66
     ambiguity
    0.66
     convergence
    0.65
     dynam
    0.64
    Activations Density 0.053%

    No Known Activations