© 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. 1790
    Prev
    Next
    INDEX
    Explanations

    instances of the word "refer" and its variations indicating citation or reference in a context

    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
     mascul
    -0.72
    fy
    -0.72
    --------------------
    -0.68
     mathemat
    -0.63
    ministic
    -0.63
     contrace
    -0.61
    dies
    -0.61
     frank
    -0.59
    iated
    -0.59
    provided
    -0.57
    POSITIVE LOGITS
    ombo
    0.76
    */(
    0.69
    selage
    0.69
    ndum
    0.69
    cking
    0.67
    catentry
    0.66
    enhagen
    0.65
    alys
    0.64
    usat
    0.63
    amily
    0.62
    Activations Density 0.027%

    No Known Activations