© 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. 3021
    Prev
    Next
    INDEX
    Explanations

    the term "those" associated with statistical data or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.92
    terday
    -0.83
    ethe
    -0.80
    ription
    -0.80
    lio
    -0.78
    escription
    -0.78
    ocate
    -0.78
    soever
    -0.77
    ntil
    -0.76
    rament
    -0.75
    POSITIVE LOGITS
     exiting
    0.76
     returning
    0.74
     thrown
    0.74
     responsible
    0.74
     stranded
    0.70
     behind
    0.67
     cance
    0.67
     stopping
    0.67
     killed
    0.66
     flown
    0.66
    Activations Density 0.029%

    No Known Activations