© 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. 1380
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Any" related to various contexts or requests for options

    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
    YR
    -0.77
     partName
    -0.67
     induction
    -0.61
    agall
    -0.61
    rha
    -0.59
     coron
    -0.57
     Tradable
    -0.56
    illance
    -0.56
     bailed
    -0.56
    essional
    -0.56
    POSITIVE LOGITS
    ways
    0.86
    time
    0.79
    baugh
    0.73
    phalt
    0.72
     mater
    0.70
     difference
    0.68
    WAYS
    0.65
    more
    0.63
     accur
    0.62
    lance
    0.60
    Activations Density 0.034%

    No Known Activations