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

    Neuronpedia

    INDEX
    Explanations

    links and specific instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to navigating websites and online interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     morale
    -0.73
     uncond
    -0.72
    ajor
    -0.71
     improv
    -0.69
     deserved
    -0.69
     virt
    -0.66
    unker
    -0.66
     retaliate
    -0.65
     dearly
    -0.65
     enrich
    -0.64
    POSITIVE LOGITS
     menus
    1.18
    pages
    1.11
    menu
    0.99
     menu
    0.99
     scroll
    0.95
     listings
    0.94
     accessed
    0.93
     popup
    0.91
     Scroll
    0.90
    tons
    0.90
    Act Density 0.783%

    No Known Activations