© 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. 1158
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "most" and its comparative or superlative context

    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
    bour
    -0.70
    tumblr
    -0.70
    Profile
    -0.68
    pron
    -0.68
    sector
    -0.67
    origin
    -0.67
    je
    -0.66
    manent
    -0.65
    hold
    -0.64
    ney
    -0.63
    POSITIVE LOGITS
     Committees
    0.79
     Heads
    0.79
     worlds
    0.75
     throats
    0.75
     Guidelines
    0.70
     vacancies
    0.68
     heels
    0.67
     roles
    0.66
     dinners
    0.66
     Authority
    0.66
    Activations Density 0.020%

    No Known Activations