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. 610
    Prev
    Next
    INDEX
    Explanations

    words related to defining or classifying terms

    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
    ton
    -0.76
    lets
    -0.68
     Richards
    -0.65
     Dickinson
    -0.65
    ayson
    -0.64
     Hew
    -0.62
     Sussex
    -0.61
    sic
    -0.60
    neath
    -0.60
    heads
    -0.59
    POSITIVE LOGITS
    ":"/
    0.79
    ROR
    0.78
    acters
    0.75
    geoning
    0.66
    ventional
    0.64
    ioned
    0.64
    agame
    0.63
    opher
    0.62
    agues
    0.61
    �
    0.61
    Activations Density 0.911%

    No Known Activations