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. 116
    Prev
    Next
    INDEX
    Explanations

    phrases that denote preferences or affiliations with individuals or groups

    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
    theless
    -0.81
    cffff
    -0.76
     discard
    -0.76
     disse
    -0.74
     ingest
    -0.70
     elig
    -0.69
    rent
    -0.68
    cellaneous
    -0.67
    farm
    -0.67
     scaven
    -0.66
    POSITIVE LOGITS
    ��
    0.93
     Vive
    0.89
     Gears
    0.78
     Yor
    0.73
     Arnold
    0.73
     Irving
    0.73
     Tesla
    0.72
     Musk
    0.72
     Eliot
    0.72
     Shake
    0.71
    Activations Density 0.061%

    No Known Activations