© 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. 2326
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and its contextual associations within phrases

    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
    kell
    -0.79
    BN
    -0.74
    otte
    -0.73
    apple
    -0.72
    iang
    -0.70
    adows
    -0.69
    ç
    -0.69
    bors
    -0.68
    ares
    -0.67
    lov
    -0.67
    POSITIVE LOGITS
     CARE
    0.78
     unst
    0.69
     process
    0.66
     ethos
    0.66
     limp
    0.65
     eye
    0.63
     deliber
    0.63
     unfolding
    0.62
     Idle
    0.62
     immedi
    0.61
    Activations Density 0.187%

    No Known Activations