© 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. 990
    Prev
    Next
    INDEX
    Explanations

    elements associated with beverages and ingredients

    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
    Ire
    -0.62
    �
    -0.61
    mins
    -0.59
    646
    -0.59
    ETH
    -0.59
    �
    -0.58
    bold
    -0.57
     Hamp
    -0.57
    ofi
    -0.57
    ミ
    -0.57
    POSITIVE LOGITS
     Wra
    0.73
     Streaming
    0.64
     offic
    0.60
     spectator
    0.58
     Argument
    0.58
     reluct
    0.58
    olia
    0.57
     ado
    0.57
    aghetti
    0.57
     depict
    0.56
    Activations Density 1.361%

    No Known Activations