© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1235
    Prev
    Next
    INDEX
    Explanations

    statistics related to damage and abilities in a gaming context

    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
     Hirosh
    -0.71
     Siri
    -0.66
     Daesh
    -0.64
     helicopters
    -0.64
     cleaner
    -0.61
     mosqu
    -0.60
    Daddy
    -0.59
     Directions
    -0.58
     Hik
    -0.58
     Brigade
    -0.58
    POSITIVE LOGITS
     piety
    0.83
    ause
    0.81
     granting
    0.77
     proc
    0.77
    gression
    0.75
     (<
    0.73
     enchantment
    0.72
     pact
    0.71
    iture
    0.69
    itu
    0.67
    Activations Density 0.311%

    No Known Activations