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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1837
    Prev
    Next
    INDEX
    Explanations

    activities related to data processing and management

    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
    mares
    -0.73
     Hoover
    -0.69
     Matters
    -0.66
    maxwell
    -0.66
    moon
    -0.64
    ��
    -0.64
     Parables
    -0.63
    raq
    -0.61
    anders
    -0.61
     Frazier
    -0.61
    POSITIVE LOGITS
     quicker
    0.87
     correctly
    0.78
     outright
    0.77
     using
    0.76
     manually
    0.76
     simultaneously
    0.75
     properly
    0.73
     faster
    0.72
     sufficiently
    0.72
     locally
    0.71
    Activations Density 0.511%

    No Known Activations