© 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. 789
    Prev
    Next
    INDEX
    Explanations

    terms related to suitability and appropriateness

    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
    sav
    -0.81
    Introduced
    -0.65
     ster
    -0.62
     gracious
    -0.62
    Sov
    -0.62
    cest
    -0.57
    �
    -0.56
     unsur
    -0.56
    ノ
    -0.56
     undefined
    -0.56
    POSITIVE LOGITS
     for
    0.83
     during
    0.71
    ulum
    0.69
     throughout
    0.66
     across
    0.64
    bernatorial
    0.61
     from
    0.61
    iesel
    0.61
     to
    0.61
    ibl
    0.60
    Activations Density 0.177%

    No Known Activations