© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1111
    Prev
    Next
    INDEX
    Explanations

    the word "Everything" and its variants indicating a focus on comprehensive or all-encompassing statements

    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
    few
    -0.73
    Bound
    -0.73
    Args
    -0.73
    catentry
    -0.71
    oard
    -0.70
    Reader
    -0.69
    パ
    -0.69
    ーティ
    -0.68
    Tri
    -0.67
     rall
    -0.66
    POSITIVE LOGITS
     else
    0.95
     revolves
    0.82
     Else
    0.79
     culmin
    0.69
     goes
    0.69
     relates
    0.69
     was
    0.68
     went
    0.68
     reflects
    0.68
    chy
    0.67
    Activations Density 0.034%

    No Known Activations