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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 391
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases indicating a minimum or baseline condition

    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
    orean
    -0.65
     audition
    -0.63
    �
    -0.62
     bilingual
    -0.62
     appeal
    -0.61
     compete
    -0.61
     competition
    -0.61
     boxed
    -0.61
    者
    -0.59
     annex
    -0.57
    POSITIVE LOGITS
    nil
    0.88
    acea
    0.83
    fortunately
    0.80
    ravis
    0.79
    VIDIA
    0.78
    last
    0.77
    heres
    0.76
    iatus
    0.75
    thens
    0.74
    poses
    0.73
    Activations Density 0.023%

    No Known Activations