© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3180
    Prev
    Next
    INDEX
    Explanations

    the pronoun "they" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     watches
    -0.82
     hears
    -0.75
     dreaming
    -0.70
     vows
    -0.70
     trusts
    -0.70
     wishes
    -0.69
     fights
    -0.69
     knows
    -0.69
     wants
    -0.68
     sees
    -0.65
    POSITIVE LOGITS
     contain
    1.09
    're
    1.04
     belong
    1.03
     include
    1.03
     consist
    1.01
     expire
    0.99
     entail
    0.98
     comprise
    0.98
     resemble
    0.98
     occur
    0.98
    Activations Density 0.115%

    No Known Activations