Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 611
    Prev
    Next
    INDEX
    Explanations

    roles related to contributions and recognition in creative or editorial contexts

    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
    ichick
    -0.75
    aird
    -0.68
    hou
    -0.68
    RAL
    -0.66
    rocket
    -0.66
    mail
    -0.66
    hett
    -0.66
    ocked
    -0.65
    creen
    -0.64
    tails
    -0.64
    POSITIVE LOGITS
    ity
    0.76
     insight
    0.72
     witness
    0.69
     insights
    0.69
     subsystem
    0.67
    Init
    0.67
     Reading
    0.67
     snippet
    0.67
     incorpor
    0.65
    ctors
    0.65
    Activations Density 1.005%

    No Known Activations