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. 82
    Prev
    Next
    INDEX
    Explanations

    rules or restrictions on commenting in discussions

    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
    lear
    -0.90
    kered
    -0.77
    cephal
    -0.75
    chi
    -0.75
    ggle
    -0.72
    liga
    -0.71
     overs
    -0.71
    assi
    -0.66
    ffee
    -0.65
    perm
    -0.65
    POSITIVE LOGITS
    icity
    0.75
    igation
    0.71
    sic
    0.66
    uin
    0.65
    oil
    0.64
    Dialogue
    0.63
    esa
    0.63
     helm
    0.63
     HMS
    0.63
     srfAttach
    0.62
    Activations Density 1.513%

    No Known Activations