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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 268
    Prev
    Next
    INDEX
    Explanations

    the pronoun "she" in various 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
    natureconservancy
    -0.87
    ���
    -0.69
    EGIN
    -0.64
    �
    -0.64
    actionDate
    -0.64
     Brenda
    -0.62
    udeb
    -0.62
    OUND
    -0.62
    ��
    -0.62
     chromosome
    -0.61
    POSITIVE LOGITS
     clears
    0.77
     flies
    0.76
     rises
    0.74
     adds
    0.74
     climbs
    0.74
     smokes
    0.72
     raises
    0.72
     carries
    0.72
     identifies
    0.71
     travels
    0.70
    Activations Density 0.133%

    No Known Activations