© 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. 3005
    Prev
    Next
    INDEX
    Explanations

    references to the ages of children

    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
    SPONSORED
    -0.84
    ccording
    -0.74
     Invention
    -0.71
    abilia
    -0.71
    ciating
    -0.69
     [|
    -0.67
     Tradable
    -0.67
     Reasons
    -0.65
     Belief
    -0.64
    ipedia
    -0.63
    POSITIVE LOGITS
    anwhile
    0.70
     embargo
    0.64
     vet
    0.64
     equ
    0.62
    mouth
    0.61
     quar
    0.61
    MpServer
    0.61
     orient
    0.60
    grade
    0.60
     timers
    0.60
    Activations Density 0.042%

    No Known Activations