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

    Neuronpedia

    INDEX
    Explanations

    references to vehicles and driving-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to vehicles and traffic-related situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cured
    -0.75
     cures
    -0.75
     marrow
    -0.75
     Tempest
    -0.73
    İĭ
    -0.72
     cure
    -0.72
    nets
    -0.71
     recipes
    -0.66
     Recipes
    -0.65
    illet
    -0.64
    POSITIVE LOGITS
     pedestrians
    1.18
     approaching
    1.03
     greeting
    0.99
     parked
    0.97
     waving
    0.96
     politely
    0.95
     motorists
    0.93
     passers
    0.92
     glances
    0.90
     bicycl
    0.89
    Act Density 0.531%

    No Known Activations