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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of external sources or references

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

    "outside" or "external"

    np_acts-logits-general · gemini-2.0-flash

    outside and external phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.76
    ToScroll
    -0.66
     EconPapers
    -0.62
    TableData
    -0.62
    webElementXpaths
    -0.58
    multirow
    -0.58
    harusnya
    -0.57
     الحره
    -0.55
    исленность
    -0.54
    > 
    -0.54
    POSITIVE LOGITS
    outside
    1.24
     Outside
    1.23
    OUTSIDE
    1.19
     OUTSIDE
    1.18
    Outside
    1.17
     outside
    1.16
     afuera
    1.01
     Exter
    0.94
     extern
    0.93
     Exterior
    0.92
    Act Density 0.176%

    No Known Activations