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. 9-TRES-DC
    5. 624
    Prev
    Next
    INDEX
    Explanations

    references to pre-ordering concepts

    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
     Parenthood
    -0.71
    eele
    -0.68
     GOODMAN
    -0.68
     toget
    -0.66
    =#
    -0.65
    rocket
    -0.64
     marginalized
    -0.61
     adolesc
    -0.61
     fingerprints
    -0.59
     Roundup
    -0.59
    POSITIVE LOGITS
    occupied
    0.85
    do
    0.83
    plan
    0.82
    vent
    0.80
    cluding
    0.78
    dos
    0.77
    ordered
    0.77
    cludes
    0.76
    cluded
    0.76
    iverpool
    0.73
    Activations Density 0.008%

    No Known Activations