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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1241
    Prev
    Next
    INDEX
    Explanations

    phrases indicating duration or time taken for tasks

    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
    irection
    -0.71
    hearted
    -0.66
     Flavoring
    -0.64
    oof
    -0.63
    bos
    -0.62
     avoiding
    -0.61
     stumbling
    -0.61
     saving
    -0.60
     Logged
    -0.60
     inhib
    -0.59
    POSITIVE LOGITS
    ェ
    0.73
     restore
    0.71
    STATE
    0.65
     merge
    0.65
     merged
    0.64
     rewrite
    0.62
    ryu
    0.62
     propagate
    0.62
     rebuild
    0.61
     Trigger
    0.61
    Activations Density 0.052%

    No Known Activations