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. 110
    Prev
    Next
    INDEX
    Explanations

    references to penal elements or attributes in a context related to societal issues

    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
    imore
    -0.80
    ilts
    -0.75
     CoC
    -0.70
     Orn
    -0.66
    office
    -0.62
    ]}
    -0.62
    housing
    -0.62
     shotguns
    -0.61
     Skydragon
    -0.61
     Household
    -0.60
    POSITIVE LOGITS
    itionally
    0.74
    龍
    0.74
    uted
    0.71
    �
    0.66
    cribed
    0.64
    llo
    0.63
    antly
    0.63
    nell
    0.62
    ante
    0.62
    acio
    0.62
    Activations Density 0.050%

    No Known Activations