© 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. 1840
    Prev
    Next
    INDEX
    Explanations

    references to a structured approach or strategy

    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
     envy
    -0.70
     hes
    -0.65
     respons
    -0.64
     dab
    -0.64
     Mubarak
    -0.63
    inventoryQuantity
    -0.63
     practices
    -0.62
     Ruin
    -0.61
     brightest
    -0.61
    isms
    -0.60
    POSITIVE LOGITS
    ��
    0.84
    ariat
    0.77
     Collider
    0.77
    atoes
    0.74
    #$
    0.73
    itialized
    0.72
    eton
    0.72
    ilts
    0.71
    xual
    0.70
    ym
    0.69
    Activations Density 0.077%

    No Known Activations