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. 96
    Prev
    Next
    INDEX
    Explanations

    references to children or child-related issues

    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
    nas
    -0.71
     NAD
    -0.65
    aceae
    -0.64
     Voyager
    -0.63
     Mothers
    -0.61
    amation
    -0.61
     Obst
    -0.61
    amara
    -0.60
     Overt
    -0.60
    Parents
    -0.60
    POSITIVE LOGITS
    ridges
    0.94
    gro
    0.84
    hood
    0.78
    ridge
    0.74
    ress
    0.74
    ple
    0.66
     star
    0.65
    merce
    0.65
    ish
    0.63
    ishly
    0.63
    Activations Density 0.041%

    No Known Activations