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. 331
    Prev
    Next
    INDEX
    Explanations

    elements related to dates and associated events

    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
    pend
    -0.65
    ADS
    -0.65
    senal
    -0.63
    pread
    -0.63
    ヘ
    -0.60
    �醒
    -0.59
    aval
    -0.58
     reckoned
    -0.58
    cow
    -0.58
    isted
    -0.58
    POSITIVE LOGITS
     panels
    0.64
    estones
    0.63
     gui
    0.61
     footsteps
    0.60
     cabinets
    0.60
     lamps
    0.59
    alias
    0.57
     cafes
    0.57
    onica
    0.56
     Pool
    0.56
    Activations Density 0.060%

    No Known Activations