© 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. 3046
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of production or creation

    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
    ��
    -1.02
    OY
    -0.80
    Rex
    -0.79
    Va
    -0.77
    aver
    -0.77
    GV
    -0.76
    hair
    -0.76
    UA
    -0.76
    UK
    -0.73
    HQ
    -0.71
    POSITIVE LOGITS
     pamph
    0.85
     advis
    0.81
     trickle
    0.72
     condos
    0.69
     rubble
    0.68
     essays
    0.67
     anecd
    0.65
     headlines
    0.64
     parach
    0.64
     lectures
    0.64
    Activations Density 0.085%

    No Known Activations