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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 429
    Prev
    Next
    INDEX
    Explanations

    phrases that begin with "We" indicating collective statements or actions

    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
    Reviewer
    -0.74
     misfortune
    -0.73
     totality
    -0.70
     Failure
    -0.66
     millenn
    -0.60
     looting
    -0.60
     denying
    -0.58
    Contents
    -0.57
     brittle
    -0.57
    REDACTED
    -0.57
    POSITIVE LOGITS
    're
    1.15
    ighed
    1.03
    'll
    1.00
    eding
    0.94
    've
    0.91
    akening
    0.90
    'd
    0.88
    akens
    0.78
    eks
    0.78
    imar
    0.76
    Activations Density 0.101%

    No Known Activations