© 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. 946
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     may
    -1.05
     will
    -1.04
     is
    -1.03
     cannot
    -1.03
     shouldn
    -1.02
     seemed
    -1.02
     seems
    -1.00
     are
    -0.99
     could
    -0.98
     would
    -0.98
    POSITIVE LOGITS
    SPONSORED
    0.55
    `.
    0.52
     juggling
    0.52
    eff
    0.51
     comprom
    0.50
     continuation
    0.50
     inhib
    0.49
     declining
    0.49
     inconsistent
    0.49
     consequ
    0.48
    Activations Density 0.468%

    No Known Activations