© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1914
    Prev
    Next
    INDEX
    Explanations

    variants of the words "recognize" and "ignore."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rians
    -0.75
    EStreamFrame
    -0.70
     GP
    -0.68
    BuyableInstoreAndOnline
    -0.65
    rian
    -0.64
    Els
    -0.64
    nels
    -0.62
    nel
    -0.62
    poons
    -0.60
    cles
    -0.59
    POSITIVE LOGITS
    ying
    0.76
    ition
    0.74
    izing
    0.73
    action
    0.73
    itive
    0.72
    ied
    0.70
    icipated
    0.67
    ipe
    0.67
    itiveness
    0.67
    ITE
    0.66
    Activations Density 0.062%

    No Known Activations