© 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. 833
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their positive attributes

    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
    rax
    -0.64
    uristic
    -0.59
    odox
    -0.57
    arthy
    -0.57
    owa
    -0.57
     forfe
    -0.56
     sovere
    -0.55
     exting
    -0.54
    assad
    -0.53
    national
    -0.53
    POSITIVE LOGITS
    lihood
    0.75
    ification
    0.71
    cies
    0.63
    Boss
    0.62
    having
    0.60
    erences
    0.60
     whom
    0.60
    ulations
    0.60
    ュ
    0.60
     apiece
    0.59
    Activations Density 0.089%

    No Known Activations