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. 107
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "depending."

    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
    BSD
    -0.73
    itsch
    -0.71
    cknow
    -0.70
    cks
    -0.70
    nos
    -0.68
    nown
    -0.67
    glers
    -0.67
    nob
    -0.66
    comed
    -0.65
    Grab
    -0.64
    POSITIVE LOGITS
     how
    0.85
     blaster
    0.69
     whether
    0.68
     what
    0.66
     who
    0.63
     intent
    0.62
    intent
    0.61
     why
    0.61
    how
    0.61
    detail
    0.60
    Activations Density 0.049%

    No Known Activations