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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 395
    Prev
    Next
    INDEX
    Explanations

    references to time periods, specifically weeks and months

    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
    relations
    -0.67
    hops
    -0.63
    psc
    -0.61
    taboola
    -0.61
     pedest
    -0.60
    ufact
    -0.60
    sure
    -0.59
    gener
    -0.58
    etheless
    -0.58
    NetMessage
    -0.58
    POSITIVE LOGITS
     however
    0.71
    Merit
    0.69
    ,
    0.69
    !,
    0.62
     ATF
    0.57
    PLA
    0.55
    ,[
    0.54
     ,
    0.54
    IFA
    0.54
     Chomsky
    0.54
    Activations Density 0.103%

    No Known Activations