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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 604
    Prev
    Next
    INDEX
    Explanations

    phrases indicating answers or solutions to questions

    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
    MRI
    -0.84
    amph
    -0.70
     preced
    -0.68
     cath
    -0.64
    aganda
    -0.62
    ixtape
    -0.62
    haven
    -0.61
    awa
    -0.61
    BOOK
    -0.60
    ↑
    -0.60
    POSITIVE LOGITS
    Shape
    0.65
     yourselves
    0.63
    IDENT
    0.63
    yip
    0.63
     YOUR
    0.61
    田
    0.61
    Low
    0.60
    Redd
    0.59
     your
    0.58
     this
    0.57
    Activations Density 0.241%

    No Known Activations