© 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. 939
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" indicating existence and state

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    eva
    -0.77
     Duchess
    -0.68
    mble
    -0.66
    veland
    -0.65
    Sense
    -0.64
     Trafford
    -0.64
    hyde
    -0.63
    llular
    -0.63
     ARTICLE
    -0.63
     Debate
    -0.62
    POSITIVE LOGITS
    ums
    0.86
    wolves
    0.79
     manifestations
    0.77
     depress
    0.77
     relics
    0.75
     fronts
    0.74
     indications
    0.74
    oys
    0.74
     undermin
    0.73
     reflections
    0.73
    Activations Density 0.285%

    No Known Activations