© 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. 1526
    Prev
    Next
    INDEX
    Explanations

    key terms related to environmental and technological themes

    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
     caliphate
    -0.62
     emperor
    -0.60
    interstitial
    -0.57
     shower
    -0.56
     superpower
    -0.55
     pronoun
    -0.55
     cartel
    -0.55
     comma
    -0.54
     rhy
    -0.54
     encyclopedia
    -0.54
    POSITIVE LOGITS
    isks
    0.64
    omas
    0.64
    ivas
    0.64
    acements
    0.61
    clips
    0.60
     alike
    0.59
    goers
    0.57
    cules
    0.57
    IGHTS
    0.56
    istically
    0.55
    Activations Density 0.920%

    No Known Activations