© 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. 718
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there" indicating statistical mentions or statements

    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
     Agric
    -0.77
    姫
    -0.75
     prest
    -0.69
     Ask
    -0.67
     phrases
    -0.66
     Lose
    -0.64
     Sell
    -0.63
    soDeliveryDate
    -0.62
     Pf
    -0.62
     heights
    -0.62
    POSITIVE LOGITS
    ItemTracker
    0.76
    ception
    0.75
    >[
    0.73
    abase
    0.72
    duction
    0.72
    after
    0.67
    aver
    0.67
    juven
    0.66
    hemer
    0.65
    Jes
    0.65
    Activations Density 0.072%

    No Known Activations