© 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. 3036
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or sentence endings

    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
     commute
    -0.75
     forbid
    -0.75
    unction
    -0.64
     legalized
    -0.64
     statewide
    -0.61
     consolid
    -0.61
     power
    -0.61
     convenience
    -0.61
     tolerate
    -0.60
     curb
    -0.60
    POSITIVE LOGITS
     Someone
    0.77
     Waves
    0.76
     Passenger
    0.74
     Calling
    0.73
     Closing
    0.71
     Others
    0.69
     Another
    0.69
     Returning
    0.69
     Towards
    0.68
     One
    0.68
    Activations Density 0.684%

    No Known Activations