© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2273
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and purchases

    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
     prayer
    -0.61
     Prayer
    -0.59
     invests
    -0.56
     welf
    -0.56
     surv
    -0.56
     Spending
    -0.55
     investing
    -0.54
    ership
    -0.54
    Jew
    -0.53
     patrol
    -0.53
    POSITIVE LOGITS
    fect
    0.67
    handle
    0.65
    pressure
    0.65
    aws
    0.63
    legraph
    0.63
    azon
    0.63
    iola
    0.63
    about
    0.61
    apult
    0.61
    ypes
    0.60
    Activations Density 0.199%

    No Known Activations