Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 479
    Prev
    Next
    INDEX
    Explanations

    phrases relating to estimated monetary values and financial assessments

    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
    mone
    -0.74
    redited
    -0.64
     Skydragon
    -0.64
    cation
    -0.61
    bis
    -0.61
    helm
    -0.61
    oran
    -0.60
    uria
    -0.59
    vernment
    -0.58
    tnc
    -0.58
    POSITIVE LOGITS
     costing
    0.87
     estimated
    0.87
    approximately
    0.87
     upwards
    0.87
     totaling
    0.84
     worth
    0.83
     tot
    0.83
    maximum
    0.83
     ranging
    0.82
     valued
    0.82
    Activations Density 1.673%

    No Known Activations