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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific words or phrases related to "box"

    oai_token-act-pair · gpt-3.5-turbo

    references to box office performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.83
     Hots
    -0.78
    uates
    -0.76
    uating
    -0.74
    uated
    -0.74
    vironment
    -0.70
    baugh
    -0.69
     GOODMAN
    -0.69
     Lauder
    -0.69
    uate
    -0.68
    POSITIVE LOGITS
    box
    1.03
    boxes
    1.03
    cars
    0.99
    buster
    0.96
    ers
    0.95
    sets
    0.93
     boxes
    0.90
    nut
    0.89
    door
    0.89
    car
    0.87
    Act Density 0.033%

    No Known Activations