Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 98
    Prev
    Next
    INDEX
    Explanations

    instances of the word "offer" and its variations in different contexts

    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
    anton
    -0.80
    rez
    -0.79
    ovember
    -0.76
    士
    -0.75
     GOODMAN
    -0.72
    DEM
    -0.70
    NING
    -0.70
    neau
    -0.69
    GM
    -0.68
    onom
    -0.67
    POSITIVE LOGITS
     imitation
    0.73
     tut
    0.69
     apprentices
    0.67
     mileage
    0.67
     penetration
    0.66
     ast
    0.66
     sleeper
    0.66
     singers
    0.65
     worsh
    0.64
     apprentice
    0.64
    Activations Density 0.043%

    No Known Activations