© 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. 983
    Prev
    Next
    INDEX
    Explanations

    words that contain the letter 'p', 'j', 't', or 'm' with high frequency

    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
     Piano
    -0.61
     Notting
    -0.61
    utsche
    -0.60
    OTE
    -0.60
    uart
    -0.59
    abe
    -0.58
     Freddie
    -0.57
     Clock
    -0.56
    ipation
    -0.56
     Lauder
    -0.55
    POSITIVE LOGITS
    arching
    0.66
    ruciating
    0.64
    pmwiki
    0.58
    etimes
    0.58
    worldly
    0.57
     whirlwind
    0.56
    sed
    0.56
     scor
    0.56
     Univers
    0.55
    angled
    0.55
    Activations Density 0.108%

    No Known Activations