© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 2563
    Prev
    Next
    INDEX
    Explanations

    references to health care and its impact on society

    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
    cyclopedia
    -0.69
     constitu
    -0.67
    romeda
    -0.65
    itialized
    -0.63
    fledged
    -0.62
     TAMADRA
    -0.62
    ustainable
    -0.62
     sanity
    -0.62
     sane
    -0.61
    hire
    -0.59
    POSITIVE LOGITS
    lessness
    0.97
     incorrect
    0.97
     inconsist
    0.95
     nowhere
    0.89
     inaccurate
    0.89
    lost
    0.88
     poorly
    0.88
     wrong
    0.87
     insufficient
    0.87
     incorrectly
    0.87
    Activations Density 2.747%

    No Known Activations