© 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. 452
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Atabek."

    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
    Effective
    -0.76
    lance
    -0.75
    buster
    -0.73
    tro
    -0.68
    offer
    -0.64
    staking
    -0.63
     srfAttach
    -0.63
     Deliver
    -0.62
    theless
    -0.61
    assetsadobe
    -0.60
    POSITIVE LOGITS
    ribute
    0.88
    ional
    0.77
    oria
    0.76
    rib
    0.74
    isma
    0.70
    que
    0.67
    rav
    0.67
    riot
    0.66
    ala
    0.66
    rio
    0.65
    Activations Density 0.033%

    No Known Activations