© 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. 450
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "have" in various contexts

    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
    cone
    -0.72
    soType
    -0.63
    mite
    -0.63
     refers
    -0.62
    Cass
    -0.61
    asuring
    -0.61
    cci
    -0.60
    soDeliveryDate
    -0.60
    fficient
    -0.59
     includ
    -0.59
    POSITIVE LOGITS
     dignity
    0.74
    oken
    0.72
     legitimacy
    0.68
     pled
    0.67
     validity
    0.67
     fallen
    0.65
     stolen
    0.65
    ollen
    0.64
    vier
    0.64
     discretion
    0.64
    Activations Density 0.128%

    No Known Activations