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. 9-TRES-DC
    5. 621
    Prev
    Next
    INDEX
    Explanations

    references to various smells

    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
    ffic
    -0.88
    oqu
    -0.73
    cil
    -0.69
    ��
    -0.64
    姫
    -0.63
    atform
    -0.62
    uchs
    -0.61
    ��
    -0.60
    Í
    -0.60
    abase
    -0.60
    POSITIVE LOGITS
     Dragonbound
    0.70
    loo
    0.69
     Mori
    0.67
    displayText
    0.67
     psychiat
    0.66
     Nightmares
    0.63
     Arkham
    0.63
     Sakuya
    0.63
     Leilan
    0.61
     awoke
    0.60
    Activations Density 0.093%

    No Known Activations