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. 47
    Prev
    Next
    INDEX
    Explanations

    elements related to location and levels of performance or achievement

    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
    rarily
    -0.67
    cutting
    -0.66
    lot
    -0.66
    pose
    -0.64
    chwitz
    -0.64
    Option
    -0.63
    urgy
    -0.63
    イト
    -0.62
    ractive
    -0.62
    cuts
    -0.62
    POSITIVE LOGITS
    inas
    0.62
    stood
    0.61
     Aure
    0.59
    olt
    0.58
    atal
    0.56
    enger
    0.55
     Commercial
    0.55
     Vive
    0.54
     Sao
    0.54
     Mens
    0.54
    Activations Density 1.178%

    No Known Activations