© 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. 3184
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize positions of leadership or guidance

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    inel
    -0.75
    phal
    -0.68
    affles
    -0.62
    ibling
    -0.62
    facing
    -0.62
    rency
    -0.60
     Adin
    -0.60
    reditary
    -0.60
     wisely
    -0.59
    Loading
    -0.59
    POSITIVE LOGITS
     charge
    1.01
     backlash
    0.75
     Convention
    0.72
     Coalition
    0.69
     pack
    0.69
     revolt
    0.69
     charges
    0.69
     erection
    0.69
     chorus
    0.69
     quarantine
    0.67
    Activations Density 0.039%

    No Known Activations