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. 237
    Prev
    Next
    INDEX
    Explanations

    phrases that include the term "well" followed by a hyphen and a descriptor

    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
    osate
    -0.66
     Morning
    -0.65
     Osw
    -0.63
     Investor
    -0.63
     Conor
    -0.63
     Ripple
    -0.62
     relief
    -0.62
     Roses
    -0.61
    urities
    -0.61
     Relief
    -0.61
    POSITIVE LOGITS
    beh
    0.84
     behaved
    0.84
     represented
    0.78
    represented
    0.76
    haus
    0.76
    affected
    0.72
     sidx
    0.70
     situated
    0.70
    meaning
    0.69
    oult
    0.68
    Activations Density 0.020%

    No Known Activations