© 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. 420
    Prev
    Next
    INDEX
    Explanations

    references to the Islamic State in the context of Iraq and Syria

    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
    qqa
    -0.73
    bee
    -0.70
     Dome
    -0.70
    kefeller
    -0.69
     landfill
    -0.67
     Chevrolet
    -0.66
    Blu
    -0.65
    trak
    -0.65
     Ferry
    -0.64
     lighthouse
    -0.64
    POSITIVE LOGITS
    iter
    0.76
    ahead
    0.71
    peed
    0.70
    allowed
    0.70
    tm
    0.69
    estamp
    0.69
    atem
    0.68
    uration
    0.67
    ersion
    0.67
    izable
    0.66
    Activations Density 0.014%

    No Known Activations