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. 172
    Prev
    Next
    INDEX
    Explanations

    terms related to investment and hiring in various contexts

    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
    rol
    -0.67
    raph
    -0.66
    illet
    -0.66
     Ferry
    -0.66
    oyal
    -0.65
    wyn
    -0.64
    IELD
    -0.64
    rame
    -0.57
     hous
    -0.57
     rooft
    -0.56
    POSITIVE LOGITS
    through
    0.69
    english
    0.69
    stress
    0.66
    BAT
    0.64
    eds
    0.63
    vis
    0.62
    Internal
    0.62
     abroad
    0.61
    starter
    0.60
    bley
    0.60
    Activations Density 2.217%

    No Known Activations