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. 661
    Prev
    Next
    INDEX
    Explanations

    verbs related to changes in numbers or statistics

    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
    umbered
    -0.74
    irlf
    -0.72
    aughs
    -0.67
    \":
    -0.66
    icipated
    -0.64
    OPLE
    -0.63
    REDACTED
    -0.63
    oise
    -0.62
    theless
    -0.61
    ournal
    -0.61
    POSITIVE LOGITS
     up
    0.77
     away
    0.63
     sideways
    0.62
     upwards
    0.59
    rising
    0.59
     explosion
    0.59
    asta
    0.58
     hay
    0.57
     upgr
    0.57
     deg
    0.57
    Activations Density 0.030%

    No Known Activations