© 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. 3235
    Prev
    Next
    INDEX
    Explanations

    URLs related to social media platforms, primarily Facebook and Twitter

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     MLA
    -0.79
     Dwell
    -0.71
    apist
    -0.71
     scrimmage
    -0.66
     lodge
    -0.65
     Reloaded
    -0.63
    SG
    -0.61
     Destination
    -0.61
     exhib
    -0.60
    NL
    -0.59
    POSITIVE LOGITS
    \/
    0.76
    uters
    0.74
    aciously
    0.73
    ately
    0.72
    imating
    0.68
    vell
    0.67
    ̶
    0.64
    ifully
    0.64
    lves
    0.64
    puted
    0.63
    Activations Density 0.020%

    No Known Activations