© 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. 966
    Prev
    Next
    INDEX
    Explanations

    phrases related to the release or disclosure of information to the public

    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
     VIDE
    -0.68
     Osw
    -0.66
    pload
    -0.64
     phot
    -0.63
    lighting
    -0.63
    pson
    -0.62
    etric
    -0.61
    usk
    -0.59
    aughtered
    -0.58
     jew
    -0.58
    POSITIVE LOGITS
    cule
    0.79
    abo
    0.76
    liest
    0.74
    .''.
    0.71
     :-)
    0.70
    Requirements
    0.66
    ™:
    0.64
     Bounty
    0.63
    lihood
    0.63
     Pledge
    0.63
    Activations Density 0.102%

    No Known Activations