© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 807
    Prev
    Next
    INDEX
    Explanations

    references to time and various contextual aspects surrounding 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
    vantage
    -0.71
    lance
    -0.67
    ueller
    -0.66
     CrossRef
    -0.66
    nces
    -0.64
    Interstitial
    -0.64
    stanbul
    -0.63
     ›
    -0.62
    200000
    -0.62
    ──
    -0.61
    POSITIVE LOGITS
    tein
    0.84
     proposing
    0.60
     allotted
    0.60
     awarded
    0.59
     depicted
    0.59
     listed
    0.58
     deemed
    0.58
    �
    0.58
     Morse
    0.57
     billed
    0.57
    Activations Density 0.297%

    No Known Activations