© 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. 852
    Prev
    Next
    INDEX
    Explanations

    instances of blaming and attribution of responsibility in statements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    IVES
    -0.77
    ️
    -0.76
    者
    -0.71
    シ
    -0.71
    フォ
    -0.70
    Reviewer
    -0.69
    アル
    -0.69
    reon
    -0.69
    �
    -0.68
    ocrates
    -0.67
    POSITIVE LOGITS
     shuffle
    0.76
     raid
    0.68
     backfield
    0.68
     docking
    0.68
     lineback
    0.64
     ply
    0.62
     scan
    0.61
     harvesting
    0.60
     jog
    0.59
     roast
    0.59
    Activations Density 0.264%

    No Known Activations