© 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. 3109
    Prev
    Next
    INDEX
    Explanations

    more structured sentences with the verb 'are' that indicate completion or status

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     heartbeat
    -0.66
    Cooldown
    -0.65
     demands
    -0.63
    vre
    -0.63
     Skydragon
    -0.61
     Schn
    -0.60
    FactoryReloaded
    -0.60
    ropolis
    -0.60
    ZE
    -0.60
     pockets
    -0.60
    POSITIVE LOGITS
     LAW
    0.74
    @#&
    0.67
     adequately
    0.66
    ameless
    0.63
    ple
    0.63
     culturally
    0.62
     knowledgeable
    0.62
    ethical
    0.62
    clud
    0.61
    ributed
    0.61
    Activations Density 0.223%

    No Known Activations