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

    Neuronpedia

    INDEX
    Explanations

    videos showing interactions between people

    oai_token-act-pair · gpt-3.5-turbo

    instances of videos showcasing events or actions involving people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -1.08
    soType
    -0.87
    ãĤ¦ãĤ¹
    -0.87
    ItemTracker
    -0.83
    utical
    -0.79
     proble
    -0.76
    enthal
    -0.74
    iqueness
    -0.74
    Ide
    -0.71
    iencies
    -0.71
    POSITIVE LOGITS
     narrator
    1.00
     smiling
    0.94
     grinning
    0.89
     actors
    0.86
     flashing
    0.85
     silhou
    0.82
     footage
    0.81
     kneeling
    0.81
     blonde
    0.80
     narration
    0.79
    Act Density 0.348%

    No Known Activations