© 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. 3080
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "provided"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    resa
    -0.73
    inen
    -0.70
    ón
    -0.70
    aver
    -0.69
     redes
    -0.67
    ATOR
    -0.65
    alth
    -0.64
    appropriately
    -0.64
    ACH
    -0.63
    haw
    -0.62
    POSITIVE LOGITS
    Reason
    0.66
     distraction
    0.66
     DNA
    0.64
     transitional
    0.64
     Reason
    0.62
     smoother
    0.62
    rices
    0.61
     speedy
    0.60
     confidential
    0.59
     proof
    0.59
    Activations Density 0.044%

    No Known Activations