© 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. 3351
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "according to" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    orie
    -0.71
    erker
    -0.65
    kan
    -0.60
    ynt
    -0.59
     disproportion
    -0.59
     fundament
    -0.58
     rall
    -0.58
     disadvantages
    -0.58
    dar
    -0.56
    rior
    -0.56
    POSITIVE LOGITS
     externalToEVAOnly
    0.79
    PsyNetMessage
    0.72
     to
    0.71
     To
    0.68
    MpServer
    0.67
     SetFontSize
    0.66
    pmwiki
    0.66
    TO
    0.66
    to
    0.65
    gently
    0.65
    Activations Density 0.016%

    No Known Activations