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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 231
    Prev
    Next
    INDEX
    Explanations

    key concepts and themes related to authority and evaluation

    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
     Cosponsors
    -0.83
    ��
    -0.69
    ordering
    -0.67
    REC
    -0.66
    ━
    -0.66
     reluct
    -0.65
    闘
    -0.64
    Reviewer
    -0.63
    mentation
    -0.62
    urate
    -0.62
    POSITIVE LOGITS
     Stead
    0.67
     Sic
    0.60
    arij
    0.59
    aneously
    0.57
     Fri
    0.56
     opportun
    0.56
     ($
    0.55
    idious
    0.55
     Rak
    0.55
     Pats
    0.54
    Activations Density 1.574%

    No Known Activations