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

    Neuronpedia

    INDEX
    Explanations

    action buttons or clickable features within a webpage or app interface

    oai_token-act-pair · gpt-3.5-turbo

    elements related to user interface components and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.84
    utics
    -0.81
     âĵĺ
    -0.73
    ourning
    -0.69
    arenthood
    -0.69
    aughters
    -0.63
    ushima
    -0.62
    cigarettes
    -0.61
     Sons
    -0.60
    andals
    -0.60
    POSITIVE LOGITS
     button
    1.22
     folder
    1.11
     menu
    1.06
     tool
    1.03
     plugin
    1.02
     option
    1.01
     parameter
    1.00
     tab
    1.00
     header
    0.99
     keyword
    0.98
    Act Density 0.310%

    No Known Activations