Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 357
    Prev
    Next
    INDEX
    Explanations

    instances of the word "leave" and related expressions indicating the action of leaving a mark or impression

    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
    Republic
    -0.73
    hens
    -0.71
    Sources
    -0.68
    Grant
    -0.67
    ho
    -0.67
    enic
    -0.63
    ENN
    -0.63
     Concepts
    -0.63
    icist
    -0.62
    eder
    -0.62
    POSITIVE LOGITS
    aman
    0.67
     betrayed
    0.66
    alysed
    0.65
    ocious
    0.65
     shattered
    0.63
    venge
    0.63
    uates
    0.63
    agle
    0.63
     Zar
    0.61
    uum
    0.61
    Activations Density 0.081%

    No Known Activations