© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1289
    Prev
    Next
    INDEX
    Explanations

    references to high-end devices and their functionalities

    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
    uffer
    -0.74
    oğ
    -0.71
    ovi
    -0.67
    ocl
    -0.67
    enance
    -0.65
    guide
    -0.63
    udi
    -0.63
    ashi
    -0.63
    coming
    -0.62
    obo
    -0.62
    POSITIVE LOGITS
     refriger
    0.78
     sexes
    0.77
     bathrooms
    0.75
     sleeps
    0.73
     respawn
    0.72
     indoors
    0.70
     outdoors
    0.69
     overfl
    0.69
     shampoo
    0.67
     slept
    0.67
    Activations Density 1.918%

    No Known Activations