© 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. 3313
    Prev
    Next
    INDEX
    Explanations

    references to quantity or amount

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ring
    -0.83
    ulic
    -0.82
    IPS
    -0.78
    ESE
    -0.77
    版
    -0.77
    cape
    -0.76
    FACE
    -0.75
    ounded
    -0.75
    kefeller
    -0.73
    REM
    -0.71
    POSITIVE LOGITS
     amount
    0.96
     number
    0.86
     chance
    0.80
    lihood
    0.79
     role
    0.76
     duration
    0.71
     roles
    0.71
     likelihood
    0.70
     range
    0.69
     chances
    0.68
    Activations Density 0.105%

    No Known Activations