© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 814
    Prev
    Next
    INDEX
    Explanations

    instances of the word "know" and its variations, indicating familiarity or recognition

    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
    race
    -0.68
    rouse
    -0.65
    lor
    -0.64
    leep
    -0.63
    ther
    -0.63
     mans
    -0.62
    Zone
    -0.62
    ���
    -0.62
     heirs
    -0.61
     departments
    -0.60
    POSITIVE LOGITS
     bub
    0.68
    MSN
    0.65
     Slime
    0.65
    eni
    0.63
     Bie
    0.61
    sov
    0.61
    enburg
    0.61
    udding
    0.60
     Bunker
    0.60
    bery
    0.60
    Activations Density 0.019%

    No Known Activations