© 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. 2825
    Prev
    Next
    INDEX
    Explanations

    variations of the word "own" indicating a sense of individual possession or ownership

    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
    stood
    -0.72
     dry
    -0.66
    acid
    -0.66
    lean
    -0.66
     drying
    -0.62
    cean
    -0.61
    chal
    -0.60
     storing
    -0.60
    warm
    -0.60
    dry
    -0.59
    POSITIVE LOGITS
    nant
    0.74
     tremend
    0.73
     Incarnation
    0.72
     Cosponsors
    0.68
    division
    0.65
     WAY
    0.64
    DIV
    0.63
    ennial
    0.62
    �
    0.62
    wcs
    0.62
    Activations Density 0.022%

    No Known Activations