© 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. 3336
    Prev
    Next
    INDEX
    Explanations

    mentions of concerns and responsibilities related to children's welfare

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    cture
    -0.87
    oglobin
    -0.73
    ONSORED
    -0.71
    OPLE
    -0.71
    rays
    -0.71
    someone
    -0.69
    ider
    -0.69
    users
    -0.69
    anus
    -0.69
    leck
    -0.69
    POSITIVE LOGITS
    qua
    0.67
     Aux
    0.63
     Wim
    0.60
     Ess
    0.60
     Kuala
    0.60
     Hack
    0.59
     Dyn
    0.59
     Coch
    0.58
     Es
    0.58
     BM
    0.58
    Activations Density 2.483%

    No Known Activations