© 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. 1724
    Prev
    Next
    INDEX
    Explanations

    contact information and acknowledgment sections in a document

    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
    bably
    -0.96
    esides
    -0.86
    iosyncr
    -0.80
    risome
    -0.77
    ecause
    -0.73
    everal
    -0.71
    theless
    -0.70
    hovah
    -0.69
    etheless
    -0.69
    lished
    -0.68
    POSITIVE LOGITS
     -
    1.02
     https
    1.01
     =================
    0.89
     ―
    0.88
     ►
    0.87
     --
    0.86
    Tags
    0.85
     |
    0.84
     ----
    0.84
     http
    0.80
    Activations Density 1.880%

    No Known Activations