© 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. 1322
    Prev
    Next
    INDEX
    Explanations

    monetary values and their contextual references

    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
    eno
    -0.68
    reb
    -0.63
    apps
    -0.62
    ebus
    -0.62
    requ
    -0.61
    aro
    -0.61
    akedown
    -0.60
    affe
    -0.60
    lang
    -0.59
    app
    -0.59
    POSITIVE LOGITS
     Almighty
    0.73
     bells
    0.68
     syn
    0.62
     equal
    0.60
     vest
    0.58
     Equal
    0.57
    thood
    0.57
     individuality
    0.56
    rified
    0.56
     Dragonbound
    0.55
    Activations Density 0.177%

    No Known Activations