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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2763
    Prev
    Next
    INDEX
    Explanations

    instances of the word "know" and its variants, particularly in contexts implying ignorance or lack of awareness

    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
    田
    -0.71
    leted
    -0.68
    装
    -0.67
    Stud
    -0.66
    Mp
    -0.65
    ecided
    -0.64
    TEXTURE
    -0.64
    KE
    -0.64
    onies
    -0.63
    ioned
    -0.62
    POSITIVE LOGITS
     anything
    0.77
     anybody
    0.71
     anyone
    0.69
    ught
    0.67
    anything
    0.65
    ahi
    0.65
     anywhere
    0.64
     much
    0.62
    nor
    0.62
    much
    0.62
    Activations Density 0.061%

    No Known Activations