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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 123
    Prev
    Next
    INDEX
    Explanations

    the concept of readiness or preparation for various situations

    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
    rez
    -0.81
    esa
    -0.76
    glas
    -0.75
    clus
    -0.75
    ptions
    -0.69
    gression
    -0.69
    xon
    -0.68
    uria
    -0.68
    resy
    -0.66
    dor
    -0.66
    POSITIVE LOGITS
     responsibly
    0.66
    aughtered
    0.65
     christ
    0.65
     mins
    0.64
     otherwise
    0.64
     financially
    0.63
    wired
    0.60
     fer
    0.60
     stewards
    0.59
     for
    0.59
    Activations Density 0.105%

    No Known Activations