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. 242
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "call" and its variations in context

    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
    lance
    -0.78
    lio
    -0.72
    lycer
    -0.71
    birds
    -0.70
    ends
    -0.69
    wl
    -0.69
    igraph
    -0.68
    623
    -0.68
    awaru
    -0.67
    auri
    -0.67
    POSITIVE LOGITS
     insanity
    0.69
     miracle
    0.65
     Rebellion
    0.64
     hypers
    0.64
     redd
    0.63
     anonymity
    0.63
     Dull
    0.61
     fake
    0.61
     exclus
    0.60
     hyper
    0.59
    Activations Density 0.028%

    No Known Activations