© 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. 3204
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or disbelief regarding unexpected outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     expects
    -0.66
    planes
    -0.65
     assumes
    -0.64
     2021
    -0.64
     2020
    -0.63
    ifies
    -0.62
     Whites
    -0.61
     adjusts
    -0.61
     withheld
    -0.59
     intends
    -0.59
    POSITIVE LOGITS
     succeed
    0.76
     reign
    0.75
    thora
    0.74
    lict
    0.72
    inite
    0.70
    uyomi
    0.70
     flourish
    0.69
     haunt
    0.69
     topple
    0.69
     fare
    0.68
    Activations Density 0.157%

    No Known Activations