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

    Neuronpedia

    INDEX
    Explanations

    phrases related to menu selection and options

    oai_token-act-pair · gpt-3.5-turbo

    references to menu options or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sidd
    -0.75
    女
    -0.74
     Mary
    -0.64
     Glas
    -0.64
    ioxide
    -0.63
     Archangel
    -0.63
     Fundamental
    -0.62
     Winston
    -0.61
     Sussex
    -0.60
    20439
    -0.60
    POSITIVE LOGITS
    entry
    0.96
    isine
    0.93
    cloth
    0.90
    eteria
    0.89
     menus
    0.89
    uration
    0.89
     menu
    0.86
     options
    0.86
    menu
    0.81
     choices
    0.81
    Act Density 0.026%

    No Known Activations