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. 213
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "o"

    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
    etheless
    -0.75
    ump
    -0.69
    think
    -0.64
    hold
    -0.62
    places
    -0.62
    leaf
    -0.61
    umbered
    -0.61
    idget
    -0.60
    body
    -0.60
    ifference
    -0.60
    POSITIVE LOGITS
    ================================================================
    0.74
     Finished
    0.68
    Desk
    0.67
    ewitness
    0.67
    rogen
    0.66
    lymp
    0.66
    £
    0.65
    vation
    0.64
    Results
    0.63
    gres
    0.63
    Activations Density 0.012%

    No Known Activations