© 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. 3331
    Prev
    Next
    INDEX
    Explanations

    instances of the word "accuse" and its variations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    Cola
    -0.85
    urat
    -0.76
    hib
    -0.75
    jac
    -0.73
    rets
    -0.73
    jong
    -0.72
    agher
    -0.72
    apons
    -0.71
    voy
    -0.70
    ーテ
    -0.69
    POSITIVE LOGITS
     Brewer
    0.71
     Antioch
    0.67
     Huck
    0.66
     Pinball
    0.66
     Dalton
    0.64
     Flavoring
    0.64
     colleagues
    0.63
     foreigners
    0.63
     Ninth
    0.63
     Vaughan
    0.61
    Activations Density 0.012%

    No Known Activations