© 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. 1137
    Prev
    Next
    INDEX
    Explanations

    connections and references related to financial transactions or networks

    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
     against
    -0.85
     into
    -0.84
    against
    -0.78
     toward
    -0.71
    into
    -0.67
     towards
    -0.67
     INTO
    -0.66
    Against
    -0.65
     Against
    -0.64
    join
    -0.63
    POSITIVE LOGITS
    ircraft
    0.74
    ertodd
    0.64
    psons
    0.63
     Lauder
    0.63
    inyl
    0.62
    onym
    0.62
    icone
    0.61
    orem
    0.61
    renheit
    0.60
    inem
    0.60
    Activations Density 1.286%

    No Known Activations