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. 17
    Prev
    Next
    INDEX
    Explanations

    the word "with" to indicate relationships or connections

    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
    Merit
    -0.75
    Brave
    -0.66
     Learns
    -0.62
    CF
    -0.62
     Called
    -0.61
    �
    -0.60
     Hardware
    -0.60
    Joined
    -0.59
    龍喚士
    -0.59
    BUG
    -0.59
    POSITIVE LOGITS
    draw
    0.88
    holding
    0.72
     apologies
    0.71
    drawn
    0.67
    shock
    0.67
    cill
    0.65
     its
    0.63
     congratulations
    0.62
    ��
    0.61
     reference
    0.58
    Activations Density 0.075%

    No Known Activations