© 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. 3102
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "some" 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
     Pengu
    -0.69
    vette
    -0.67
    ──
    -0.67
    ode
    -0.67
    malink
    -0.67
    asury
    -0.66
    ogun
    -0.65
    icion
    -0.64
     Donation
    -0.64
    ilial
    -0.63
    POSITIVE LOGITS
     idiots
    0.80
     giants
    0.70
     pests
    0.68
     pies
    0.68
     apples
    0.67
     dinosaurs
    0.63
     envy
    0.63
     nuts
    0.63
     Pis
    0.63
     deities
    0.63
    Activations Density 0.073%

    No Known Activations