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. 298
    Prev
    Next
    INDEX
    Explanations

    expressions of capability or ability

    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
    asking
    -0.63
     importance
    -0.62
    wise
    -0.59
     significance
    -0.55
     necessity
    -0.53
    TAG
    -0.53
    IME
    -0.53
     Mens
    -0.53
     Goldberg
    -0.52
     elig
    -0.52
    POSITIVE LOGITS
    adian
    0.93
    handle
    0.89
    't
    0.82
     handle
    0.77
    ndra
    0.74
    acus
    0.73
     withstand
    0.72
     recite
    0.72
     cope
    0.71
    ��
    0.71
    Activations Density 0.140%

    No Known Activations