© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 684
    Prev
    Next
    INDEX
    Explanations

    the phrase "has been" 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
     Aqu
    -0.68
     Nare
    -0.67
     Butterfly
    -0.67
     beginnings
    -0.62
     Charity
    -0.62
     Cov
    -0.61
     aquarium
    -0.60
     Dino
    -0.57
     Dragonbound
    -0.57
     Qian
    -0.56
    POSITIVE LOGITS
    til
    0.80
    sts
    0.72
    tal
    0.70
    iasco
    0.67
    rama
    0.66
    odcast
    0.65
    rl
    0.65
    spoken
    0.64
    process
    0.64
    ritten
    0.63
    Activations Density 0.065%

    No Known Activations