© 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. 1938
    Prev
    Next
    INDEX
    Explanations

    words related to extreme or significant conditions

    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
     boundaries
    -0.75
    BuyableInstoreAndOnline
    -0.74
    MSN
    -0.73
     Thumbnails
    -0.72
    Filename
    -0.69
     cues
    -0.68
     Extras
    -0.67
    rogens
    -0.67
     designation
    -0.65
    yles
    -0.65
    POSITIVE LOGITS
    ably
    1.30
    able
    1.02
    icable
    1.00
    isible
    0.94
    prising
    0.90
    ingly
    0.89
    vable
    0.89
    ented
    0.87
    abled
    0.87
    igent
    0.87
    Activations Density 0.119%

    No Known Activations