© 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. 3300
    Prev
    Next
    INDEX
    Explanations

    references to military involvement or actions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    �
    -0.61
     professional
    -0.59
     Slayer
    -0.57
    %%%%
    -0.57
     boxing
    -0.55
     Assault
    -0.54
     Mack
    -0.54
     Kamp
    -0.54
     Provision
    -0.53
     Rack
    -0.53
    POSITIVE LOGITS
    sie
    0.79
    rica
    0.73
    .<
    0.72
    ¨
    0.71
     involves
    0.71
    beh
    0.70
    =-=-=-=-
    0.70
    !,
    0.69
    .","
    0.68
    .</
    0.68
    Activations Density 1.677%

    No Known Activations