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

    Neuronpedia

    INDEX
    Explanations

    patterns related to examples and typical representations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Words like "typical" and "example" introducing representative instances or illustrations in academic and technical documents, often preceding figures, spectra, data outputs, or code samples.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Negative Logits
     bezpiecze
    -0.38
     basically
    -0.37
    Insee
    -0.34
     básicamente
    -0.34
    wendigkeit
    -0.33
    basically
    -0.32
     kerana
    -0.32
     postIndex
    -0.32
     télécommande
    -0.31
    alnız
    -0.31
    POSITIVE LOGITS
     Typical
    0.71
     ExecuteAsync
    0.70
    Typical
    0.69
     example
    0.68
     examples
    0.68
     Example
    0.68
    typical
    0.66
    Example
    0.65
     EXAMPLE
    0.63
     typical
    0.61
    Act Density 0.047%

    No Known Activations