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. 31
    Prev
    Next
    INDEX
    Explanations

    elements related to capability and expertise

    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
    ****************
    -0.68
     abort
    -0.63
     sensit
    -0.61
    bda
    -0.58
     tentative
    -0.58
     guiActiveUn
    -0.57
     uncertain
    -0.57
     dearly
    -0.57
    oad
    -0.57
     nervous
    -0.57
    POSITIVE LOGITS
    soever
    0.94
    nor
    0.74
    TO
    0.73
    ventus
    0.72
    to
    0.66
     Canaver
    0.66
    To
    0.65
    fi
    0.64
    jong
    0.63
     Agric
    0.62
    Activations Density 0.151%

    No Known Activations