© 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. 798
    Prev
    Next
    INDEX
    Explanations

    references to the term "President-elect."

    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
    regate
    -0.83
     Brach
    -0.72
    construct
    -0.71
    TOP
    -0.71
    Border
    -0.71
    ricular
    -0.70
    asonic
    -0.69
    Sleep
    -0.69
    uggle
    -0.67
    ═
    -0.66
    POSITIVE LOGITS
     affirmed
    0.68
     Appears
    0.68
     identified
    0.65
     deterior
    0.64
     illustrated
    0.63
    uters
    0.63
    oi
    0.61
     clar
    0.61
     betrayed
    0.61
    ohan
    0.61
    Activations Density 0.005%

    No Known Activations