© 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. 793
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and references to individuals in a political context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    abus
    -0.68
     Ended
    -0.67
    icter
    -0.65
     Leilan
    -0.64
    erman
    -0.63
    helm
    -0.63
    iscons
    -0.61
     arose
    -0.61
    ��
    -0.61
    PHOTOS
    -0.61
    POSITIVE LOGITS
     counterpart
    0.74
    innacle
    0.74
     predecessor
    0.73
    pan
    0.72
     predecessors
    0.64
    ensive
    0.63
     Aud
    0.61
     Wit
    0.61
    cest
    0.60
    FB
    0.60
    Activations Density 0.155%

    No Known Activations