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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 849
    Prev
    Next
    INDEX
    Explanations

    references to groups or categories that include "one of the" phrases followed by a specific number of entities

    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
    aminer
    -0.86
    yip
    -0.83
    maker
    -0.78
    rome
    -0.78
    heid
    -0.78
    rency
    -0.78
    abase
    -0.77
    enhagen
    -0.76
    abulary
    -0.75
    ernaut
    -0.75
    POSITIVE LOGITS
     quarters
    0.83
     scenarios
    0.82
     passengers
    0.79
     detainees
    0.78
     dstg
    0.78
     captives
    0.77
     seats
    0.76
     readings
    0.75
     guests
    0.75
     memos
    0.75
    Activations Density 0.053%

    No Known Activations