© 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. 3251
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and concerns

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    worldly
    -0.83
    エル
    -0.73
    アル
    -0.71
    Reviewer
    -0.71
    ドラゴン
    -0.70
    ework
    -0.69
    uncle
    -0.68
    ENC
    -0.68
     resil
    -0.68
    SPONSORED
    -0.68
    POSITIVE LOGITS
    ande
    0.76
     Compass
    0.68
     Petro
    0.68
     Prevention
    0.65
     Mal
    0.64
    inda
    0.63
     Shark
    0.63
     Insurance
    0.63
     Accounting
    0.62
     Forest
    0.62
    Activations Density 0.460%

    No Known Activations