© 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. 1066
    Prev
    Next
    INDEX
    Explanations

    the presence of the name "Krist" or variations of it

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ados
    -0.67
     +++
    -0.67
    cheon
    -0.62
    wark
    -0.61
    achine
    -0.60
    btn
    -0.60
    izu
    -0.60
    mun
    -0.57
     Heads
    -0.57
    dot
    -0.57
    POSITIVE LOGITS
    llah
    0.72
    animous
    0.70
    opher
    0.70
    aps
    0.67
    �
    0.65
    fty
    0.64
    offer
    0.64
    iod
    0.62
    ��
    0.61
    cale
    0.61
    Activations Density 0.061%

    No Known Activations