© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1163
    Prev
    Next
    INDEX
    Explanations

    references to military personnel and their ranks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    breeding
    -0.85
    anto
    -0.82
    oil
    -0.81
    hra
    -0.80
    merga
    -0.79
     provinces
    -0.78
    iens
    -0.78
    rosis
    -0.76
    iasis
    -0.75
    ulin
    -0.74
    POSITIVE LOGITS
     storefront
    0.86
     Snapchat
    0.85
     Arcade
    0.84
     locker
    0.83
    Interstitial
    0.81
     Splash
    0.76
    club
    0.75
     Craigslist
    0.75
     texting
    0.73
     Comedy
    0.73
    Activations Density 2.306%

    No Known Activations