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. 210
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "e" and related phonetic components in words

    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
    orthy
    -0.68
    esthetic
    -0.66
    ional
    -0.62
    icho
    -0.61
    lihood
    -0.61
     appre
    -0.61
    ITIES
    -0.61
    ó
    -0.60
    visual
    -0.60
     ré
    -0.58
    POSITIVE LOGITS
    Alias
    0.78
    dial
    0.76
     Mouth
    0.66
    ction
    0.63
     Crusade
    0.61
    idem
    0.61
    Zone
    0.61
    Palest
    0.59
    wolves
    0.59
    eteria
    0.58
    Activations Density 1.249%

    No Known Activations