© 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. 2618
    Prev
    Next
    INDEX
    Explanations

    instances of pronouns related to gender 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
    tre
    -0.75
    gaard
    -0.71
    ワ
    -0.68
    inav
    -0.67
     TRUE
    -0.67
     dstg
    -0.66
     objects
    -0.65
    arkable
    -0.64
    方
    -0.64
    BILITIES
    -0.62
    POSITIVE LOGITS
     Lana
    0.70
    toe
    0.68
     Anita
    0.65
     Rita
    0.62
     Donna
    0.61
     feminists
    0.60
     Carolyn
    0.59
    girlfriend
    0.59
    nee
    0.59
    Sorry
    0.59
    Activations Density 0.011%

    No Known Activations