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. 603
    Prev
    Next
    INDEX
    Explanations

    concepts related to underlying principles, mechanics, history, and logic

    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
     beware
    -0.72
    ector
    -0.63
    orem
    -0.63
    heit
    -0.60
    ensis
    -0.60
    hess
    -0.59
    daq
    -0.57
    ardless
    -0.57
    ifax
    -0.57
    ower
    -0.57
    POSITIVE LOGITS
     behind
    1.14
    behind
    0.93
     Behind
    0.71
     involved
    0.69
     surrounding
    0.66
     leading
    0.63
    Behind
    0.60
    among
    0.60
     of
    0.57
    ��
    0.57
    Activations Density 0.234%

    No Known Activations