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

    Neuronpedia

    INDEX
    Explanations

    instructions related to interacting with buttons or options in an interface

    oai_token-act-pair · gpt-3.5-turbo

    elements related to interactive user interface actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.88
     virginity
    -0.85
    emale
    -0.79
    ictions
    -0.73
    wives
    -0.72
    tested
    -0.72
     vows
    -0.69
    indal
    -0.69
    ctors
    -0.68
    wife
    -0.67
    POSITIVE LOGITS
     toolbar
    1.00
     sidebar
    0.88
     dashboard
    0.85
     menu
    0.81
     newsp
    0.79
     navigation
    0.78
     GUI
    0.77
     checkout
    0.76
     popup
    0.76
     pane
    0.76
    Act Density 0.213%

    No Known Activations