© 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. 3137
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "there are."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    MpServer
    -0.64
    oulos
    -0.64
    PG
    -0.63
    appa
    -0.63
    Initialized
    -0.61
    oval
    -0.61
    ミ
    -0.60
    ノ
    -0.57
    Dispatch
    -0.57
    baum
    -0.56
    POSITIVE LOGITS
     several
    1.06
     many
    1.02
     two
    0.98
     countless
    0.96
     few
    0.94
     three
    0.92
     innumerable
    0.91
     numerous
    0.89
     four
    0.87
    many
    0.84
    Activations Density 0.047%

    No Known Activations