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. 378
    Prev
    Next
    INDEX
    Explanations

    instances of the word "two" and its variations in context

    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
    eston
    -0.74
    ffen
    -0.73
    vere
    -0.72
    perse
    -0.71
    ocard
    -0.68
    mund
    -0.68
    users
    -0.67
    eno
    -0.67
    ported
    -0.66
    auder
    -0.66
    POSITIVE LOGITS
    ♦
    0.74
     dozen
    0.74
    thirds
    0.71
    Prin
    0.70
    ••
    0.66
     CFL
    0.64
    billion
    0.64
    anasia
    0.64
    dozen
    0.64
     thirds
    0.62
    Activations Density 0.029%

    No Known Activations