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. 227
    Prev
    Next
    INDEX
    Explanations

    instances of the word "When" indicating the start of a narrative or event

    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
     Originally
    -0.73
    hran
    -0.66
    war
    -0.65
     Prediction
    -0.64
    JJ
    -0.62
     Bake
    -0.61
    Py
    -0.61
    Ho
    -0.61
    nah
    -0.61
    worth
    -0.60
    POSITIVE LOGITS
     heartbeat
    0.76
    �醒
    0.76
    strate
    0.72
     examination
    0.70
     realm
    0.69
    antically
    0.69
     digest
    0.66
     indu
    0.65
     waking
    0.65
    龍�
    0.65
    Activations Density 0.277%

    No Known Activations