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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causing commotion or excitement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stir" and its variations throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    graded
    -0.79
    ework
    -0.70
    Gs
    -0.68
    urance
    -0.67
    GC
    -0.63
    KB
    -0.62
    Size
    -0.62
    prototype
    -0.61
    ighth
    -0.61
    gression
    -0.61
    POSITIVE LOGITS
     stir
    3.66
     stirring
    2.48
     stirred
    2.40
     Stir
    2.19
     swirl
    1.61
     agitation
    1.26
     simmer
    1.21
     uproar
    1.21
     ferment
    1.19
     shake
    1.16
    Act Density 0.023%

    No Known Activations