© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1489
    Prev
    Next
    INDEX
    Explanations

    phrases that reference the existence of something or make declarative statements

    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
     concludes
    -0.63
     Outbreak
    -0.61
     Summoner
    -0.60
    aver
    -0.59
    vote
    -0.58
    aroo
    -0.57
     helicop
    -0.56
     Pilgrim
    -0.56
     WARN
    -0.55
    toggle
    -0.54
    POSITIVE LOGITS
     significance
    0.75
     bound
    0.72
     importance
    0.71
     nothing
    0.71
     been
    0.69
     urgency
    0.68
     relevance
    0.67
     dignity
    0.66
     scope
    0.66
     strength
    0.65
    Activations Density 0.031%

    No Known Activations