© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1123
    Prev
    Next
    INDEX
    Explanations

    geographical location names and associated entities

    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
     parting
    -0.69
     PAN
    -0.68
     Hemp
    -0.68
    uyomi
    -0.65
     Ups
    -0.65
     Ajax
    -0.64
     Pict
    -0.64
     XT
    -0.63
     Pair
    -0.62
     Bad
    -0.62
    POSITIVE LOGITS
    emic
    0.83
    cation
    0.75
    availability
    0.72
    rg
    0.71
    killed
    0.68
    uctions
    0.67
    gettable
    0.67
    growing
    0.66
    �
    0.65
    alty
    0.65
    Activations Density 0.196%

    No Known Activations