© 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. 3161
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "has been"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    now
    -0.70
    tymology
    -0.69
    ottage
    -0.55
    495
    -0.54
     adulthood
    -0.53
    inav
    -0.53
     furthermore
    -0.53
    Role
    -0.52
    intosh
    -0.52
    ndum
    -0.51
    POSITIVE LOGITS
     gest
    0.62
     nib
    0.60
     bump
    0.58
    alyst
    0.57
    aples
    0.56
    pec
    0.55
    atem
    0.55
    atur
    0.54
    enda
    0.54
     explos
    0.54
    Activations Density 0.071%

    No Known Activations