© 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. 3077
    Prev
    Next
    INDEX
    Explanations

    negations or phrases indicating something is absent or not present

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    haven
    -0.77
    wire
    -0.75
    Ware
    -0.72
     Tycoon
    -0.69
    nikov
    -0.67
    nered
    -0.66
     Towns
    -0.66
    leave
    -0.65
    onomy
    -0.64
    imil
    -0.63
    POSITIVE LOGITS
     proble
    0.80
     anymore
    0.75
     invasive
    0.75
     compulsory
    0.75
     intrusive
    0.75
    ifax
    0.74
     exhaustive
    0.74
     ubiquitous
    0.72
     necessarily
    0.72
     causation
    0.70
    Activations Density 0.163%

    No Known Activations