© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3216
    Prev
    Next
    INDEX
    Explanations

    monetary values or financial amounts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Bosnia
    -0.64
     gentlemen
    -0.64
     orchestr
    -0.62
    ć
    -0.60
     Mirage
    -0.59
     transitional
    -0.57
     Sandra
    -0.56
     buddy
    -0.56
     older
    -0.56
     intermedi
    -0.55
    POSITIVE LOGITS
    1000
    0.77
    bilt
    0.76
    dimension
    0.76
    visor
    0.74
    IGHT
    0.73
    utterstock
    0.71
    %]
    0.71
    Volume
    0.68
    100
    0.68
    \/
    0.67
    Activations Density 0.063%

    No Known Activations