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. 329
    Prev
    Next
    INDEX
    Explanations

    expressions related to anticipation and moments before a significant event

    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
    uala
    -0.81
    argon
    -0.80
     Corruption
    -0.74
    yne
    -0.73
    eworld
    -0.72
    Dialogue
    -0.70
    ataka
    -0.69
    opath
    -0.69
    angel
    -0.68
    ials
    -0.68
    POSITIVE LOGITS
    inged
    0.71
     hope
    0.70
     breath
    0.68
     hopes
    0.68
     slim
    0.67
    ivably
    0.66
     optimism
    0.66
     imag
    0.66
     dashed
    0.65
     largeDownload
    0.64
    Activations Density 2.205%

    No Known Activations