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. 108
    Prev
    Next
    INDEX
    Explanations

    terms related to physical health

    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
    later
    -0.75
    ilts
    -0.71
    mat
    -0.69
    else
    -0.69
    lov
    -0.68
    reth
    -0.67
    atomic
    -0.67
    endif
    -0.66
    requires
    -0.65
    ordering
    -0.65
    POSITIVE LOGITS
     attest
    0.66
     tow
    0.66
     explanations
    0.65
     evid
    0.65
     therapist
    0.64
     attractiveness
    0.63
    itech
    0.62
    ight
    0.61
    arge
    0.60
     indications
    0.60
    Activations Density 0.022%

    No Known Activations