© 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. 2957
    Prev
    Next
    INDEX
    Explanations

    references to legislative actions and opposition

    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
    rug
    -0.79
    rolling
    -0.78
    iably
    -0.76
    uin
    -0.75
    umbing
    -0.73
    linger
    -0.70
    eding
    -0.70
    ACTED
    -0.70
    eus
    -0.69
    igure
    -0.69
    POSITIVE LOGITS
     referral
    0.69
     Jets
    0.67
     lear
    0.66
     weakest
    0.66
     arrangement
    0.64
     Browns
    0.63
     tactic
    0.61
     autos
    0.61
     autop
    0.60
     Istanbul
    0.60
    Activations Density 0.261%

    No Known Activations