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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a call to action or user interaction

    oai_token-act-pair · gpt-3.5-turbo

    clicks or interactions related to navigation and actions on a website

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynthesis
    -0.66
    BuyableInstoreAndOnline
    -0.65
    udeb
    -0.62
    Winter
    -0.62
    giving
    -0.60
    APD
    -0.59
    awi
    -0.58
    Fel
    -0.58
    obic
    -0.58
     minds
    -0.57
    POSITIVE LOGITS
     button
    1.13
    button
    1.03
     icon
    1.01
     buttons
    0.92
     arrow
    0.89
     [+]
    0.84
     banner
    0.84
     arrows
    0.84
     icons
    0.79
    actions
    0.77
    Act Density 0.055%

    No Known Activations