© 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. 2953
    Prev
    Next
    INDEX
    Explanations

    assertions or claims regarding authenticity and origin

    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
     lengths
    -0.83
    pmwiki
    -0.81
    faced
    -0.79
    pled
    -0.75
    TAIN
    -0.73
     サーティワン
    -0.72
    ointed
    -0.71
    ilib
    -0.69
    stood
    -0.68
    ptoms
    -0.67
    POSITIVE LOGITS
     authentic
    0.70
     apiece
    0.66
     autonomous
    0.65
     empowering
    0.63
     electing
    0.63
     franc
    0.62
     meaningful
    0.62
     fulfilling
    0.61
     belonging
    0.61
     genuine
    0.60
    Activations Density 0.223%

    No Known Activations