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. 73
    Prev
    Next
    INDEX
    Explanations

    time-related expressions indicating durations or intervals

    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
    20439
    -0.67
    yrim
    -0.66
    etta
    -0.65
    SpaceEngineers
    -0.63
     NTS
    -0.62
    imaru
    -0.61
     Pharmaceutical
    -0.61
    Switch
    -0.61
    yout
    -0.60
     Unsure
    -0.59
    POSITIVE LOGITS
     ago
    0.88
    itions
    0.82
    ago
    0.77
    angs
    0.75
     removed
    0.69
    freedom
    0.68
    sa
    0.66
     Cheong
    0.64
    quickShipAvailable
    0.64
    itional
    0.63
    Activations Density 0.040%

    No Known Activations