© 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. 3067
    Prev
    Next
    INDEX
    Explanations

    phrases expressing intention or desire

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    CLASSIFIED
    -0.75
    skinned
    -0.71
    76561
    -0.71
     millenn
    -0.67
     Rai
    -0.66
    apsed
    -0.64
    �
    -0.64
    thumbnails
    -0.62
     Mald
    -0.61
    arted
    -0.60
    POSITIVE LOGITS
     preserve
    0.76
     ensure
    0.75
     assure
    0.73
     thank
    0.73
    agine
    0.70
     commun
    0.68
     commend
    0.65
     safeguard
    0.65
     minimize
    0.64
     honor
    0.64
    Activations Density 0.066%

    No Known Activations