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. 379
    Prev
    Next
    INDEX
    Explanations

    phrases urging action or participation

    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
     derog
    -0.69
     outdoors
    -0.64
     discouraging
    -0.63
     brig
    -0.63
    Downloadha
    -0.63
    是
    -0.62
     humili
    -0.62
     handic
    -0.62
     caveats
    -0.61
     lair
    -0.61
    POSITIVE LOGITS
    eyed
    0.76
    eta
    0.75
    eded
    0.74
    cro
    0.71
    urga
    0.70
    ragon
    0.70
    eatures
    0.69
    amide
    0.69
    onde
    0.69
    ancial
    0.68
    Activations Density 0.025%

    No Known Activations