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. 9-TRES-DC
    5. 606
    Prev
    Next
    INDEX
    Explanations

    mentions of the letter "W"

    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
     lett
    -0.72
     breeze
    -0.69
     selves
    -0.67
     icons
    -0.65
    tons
    -0.65
     Lines
    -0.62
     riders
    -0.62
    framework
    -0.61
     muse
    -0.61
     Rae
    -0.61
    POSITIVE LOGITS
    uffle
    0.84
    ichita
    0.83
    rity
    0.79
    DIV
    0.79
    NPR
    0.77
    SB
    0.73
    rique
    0.71
    atos
    0.70
    raq
    0.70
    elta
    0.69
    Activations Density 0.008%

    No Known Activations