© 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. 3147
    Prev
    Next
    INDEX
    Explanations

    references to the need for companionship and support

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     reperto
    -0.77
    Hig
    -0.76
    ccording
    -0.70
    raq
    -0.69
    arez
    -0.66
    Wik
    -0.65
     Nights
    -0.65
    vim
    -0.65
    terday
    -0.64
    chuk
    -0.63
    POSITIVE LOGITS
     sucker
    0.79
     Advice
    0.73
     advise
    0.68
     advice
    0.67
     step
    0.65
     shepherd
    0.65
    alkyrie
    0.64
    ymm
    0.64
     bumps
    0.62
     giant
    0.61
    Activations Density 0.171%

    No Known Activations