© 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. 987
    Prev
    Next
    INDEX
    Explanations

    references to someone's whereabouts or destination

    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
     [|
    -0.64
     Impossible
    -0.62
    tg
    -0.60
    egal
    -0.60
     Thumbnails
    -0.59
    ESCO
    -0.58
     seams
    -0.58
    UTH
    -0.58
     Gujarat
    -0.58
    Í
    -0.57
    POSITIVE LOGITS
    onet
    0.81
     headquartered
    0.75
     ILCS
    0.68
    ole
    0.60
     numbering
    0.60
     located
    0.60
     numbered
    0.59
    dylib
    0.59
     based
    0.59
     concerned
    0.58
    Activations Density 0.076%

    No Known Activations