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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 289
    Prev
    Next
    INDEX
    Explanations

    references to promotional offers or discounts

    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
    arton
    -0.69
    ェ
    -0.67
    owan
    -0.63
     amassed
    -0.61
     appar
    -0.60
    ワ
    -0.59
    ellar
    -0.55
    wine
    -0.55
    orde
    -0.53
     upro
    -0.53
    POSITIVE LOGITS
    ering
    0.85
    spring
    0.85
    enses
    0.83
    ices
    0.79
    topic
    0.76
    hand
    0.75
    cial
    0.75
    endas
    0.74
    loading
    0.72
    ctr
    0.71
    Activations Density 0.015%

    No Known Activations