© 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. 3240
    Prev
    Next
    INDEX
    Explanations

    symbols or special characters often associated with media or broadcast contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    anza
    -0.79
    ortium
    -0.71
    idently
    -0.67
    boss
    -0.67
    packing
    -0.67
    cale
    -0.66
    yet
    -0.65
    ance
    -0.65
    patrick
    -0.64
    lihood
    -0.63
    POSITIVE LOGITS
    ��
    0.88
    ��
    0.83
    �
    0.83
    �
    0.82
    �
    0.81
    �
    0.81
    �
    0.78
    �
    0.74
    �
    0.73
    �
    0.73
    Activations Density 0.082%

    No Known Activations