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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal characteristics and occupations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social constructs and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sites
    -0.77
    hops
    -0.75
    rencies
    -0.74
    places
    -0.73
    steps
    -0.72
    prints
    -0.71
    iuses
    -0.70
    rooms
    -0.69
    rogens
    -0.68
    drops
    -0.66
    POSITIVE LOGITS
     inhibitor
    0.86
     thereof
    0.86
     thereto
    0.81
     antidote
    0.76
     mustache
    0.73
     charger
    0.73
     loader
    0.72
     accompanying
    0.71
     dose
    0.68
     indicator
    0.68
    Act Density 0.406%

    No Known Activations