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. 69
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to male and female characters

    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
    SPONSORED
    -0.80
     induce
    -0.74
    include
    -0.73
     mandate
    -0.67
    パ
    -0.64
     cause
    -0.64
    create
    -0.64
     produce
    -0.63
     denote
    -0.63
     catch
    -0.63
    POSITIVE LOGITS
     remembers
    1.11
     knows
    1.03
     believes
    1.01
     has
    1.00
     hasn
    0.97
     loves
    0.97
     deserves
    0.96
     regrets
    0.96
     awaits
    0.95
     feels
    0.93
    Activations Density 0.279%

    No Known Activations