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. 21
    Prev
    Next
    INDEX
    Explanations

    instances of the word "count" and its variations

    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
    ifax
    -0.72
    onne
    -0.69
    nesia
    -0.69
    lan
    -0.69
    stress
    -0.68
    OA
    -0.67
    ienne
    -0.67
    aunt
    -0.66
    ••
    -0.65
    ────
    -0.62
    POSITIVE LOGITS
     %%
    0.68
     plum
    0.67
    ebus
    0.66
     raspberry
    0.65
     itself
    0.62
     yourself
    0.59
    utherford
    0.58
    tops
    0.58
    ppers
    0.58
    ighth
    0.57
    Activations Density 0.014%

    No Known Activations