© 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. 2276
    Prev
    Next
    INDEX
    Explanations

    repeated references to specific individuals, particularly in pronouns and their actions

    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
     bother
    -0.68
     Sacrament
    -0.65
    Lot
    -0.64
    Hell
    -0.63
     lett
    -0.63
     foreigner
    -0.63
     Trident
    -0.62
     detrim
    -0.62
    Companies
    -0.62
     inconvenience
    -0.62
    POSITIVE LOGITS
    ather
    0.92
    avier
    0.91
    aly
    0.86
    aus
    0.83
    ooming
    0.82
    arts
    0.80
    aling
    0.79
    alia
    0.78
    conom
    0.78
    chron
    0.77
    Activations Density 0.113%

    No Known Activations