© 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. 3232
    Prev
    Next
    INDEX
    Explanations

    references to individuals with the title "Mr." followed by a name

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ��
    -0.81
    ���
    -0.66
    WIND
    -0.65
     srfAttach
    -0.60
    FIELD
    -0.60
    FORE
    -0.59
    WARE
    -0.59
    OLD
    -0.59
     captains
    -0.58
     unsus
    -0.56
    POSITIVE LOGITS
    .;
    0.92
    .),
    0.90
    .).
    0.85
    .,
    0.85
    .,"
    0.80
    ._
    0.80
    .:
    0.79
    .–
    0.77
    .—
    0.76
    .
    0.74
    Activations Density 0.026%

    No Known Activations