© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1070
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities named "Sund" and instances of notable terms

    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
     occasion
    -0.73
    Saharan
    -0.71
     Yor
    -0.70
    \<
    -0.66
     respectively
    -0.62
    の�
    -0.61
     topics
    -0.61
     cue
    -0.60
     accordingly
    -0.60
     Jarvis
    -0.60
    POSITIVE LOGITS
    minecraft
    0.79
     tremend
    0.79
    beck
    0.72
    react
    0.72
    perse
    0.70
    alk
    0.69
    inx
    0.69
    sein
    0.69
    emark
    0.68
     volunte
    0.68
    Activations Density 0.066%

    No Known Activations