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. 623
    Prev
    Next
    INDEX
    Explanations

    references to various types of professionals or creatives involved in different fields

    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
    tains
    -0.85
    pires
    -0.82
     persists
    -0.80
     haun
    -0.80
     evolves
    -0.79
     manifests
    -0.76
     hurts
    -0.76
     arises
    -0.72
     Kills
    -0.72
     occurs
    -0.72
    POSITIVE LOGITS
    '
    1.04
     themselves
    1.01
    hip
    0.86
    ']
    0.81
     haven
    0.78
     discuss
    0.78
    pace
    0.77
     weren
    0.75
     aren
    0.75
     were
    0.74
    Activations Density 0.351%

    No Known Activations