Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 270
    Prev
    Next
    INDEX
    Explanations

    instances of the word "you."

    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
    umerable
    -0.78
    SpaceEngineers
    -0.76
    Writer
    -0.63
    arial
    -0.61
    cell
    -0.60
     Typ
    -0.60
    WAR
    -0.60
     Romance
    -0.58
    problem
    -0.58
    sel
    -0.58
    POSITIVE LOGITS
    're
    0.85
     wrestle
    0.74
     organise
    0.73
     equip
    0.73
     specialize
    0.73
     recognise
    0.72
     prioritize
    0.71
     know
    0.71
     recognize
    0.71
     are
    0.68
    Activations Density 0.102%

    No Known Activations