© 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. 3347
    Prev
    Next
    INDEX
    Explanations

    phrases related to forms and error messages in online interactions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     explanations
    -0.76
    ifications
    -0.74
    usions
    -0.68
     conclusions
    -0.67
     parallels
    -0.65
    anges
    -0.64
     evid
    -0.64
     distilled
    -0.63
     theories
    -0.63
     springs
    -0.63
    POSITIVE LOGITS
    Jar
    0.62
     clipping
    0.62
    HUD
    0.59
    Mass
    0.59
    hod
    0.58
    LOD
    0.57
    DM
    0.57
    roid
    0.57
    hood
    0.57
    health
    0.56
    Activations Density 0.029%

    No Known Activations