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

    Neuronpedia

    INDEX
    Explanations

    words related to containers or packages

    oai_token-act-pair · gpt-3.5-turbo

    references to "box" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.80
     Hots
    -0.80
    uated
    -0.80
    vironment
    -0.77
    uating
    -0.75
    uates
    -0.75
    ittee
    -0.73
    FUL
    -0.71
    baugh
    -0.71
     Archdemon
    -0.66
    POSITIVE LOGITS
     boxes
    1.01
    boxes
    1.01
    box
    0.99
    cars
    0.99
     box
    0.94
    buster
    0.86
     Box
    0.85
    Box
    0.85
    nut
    0.84
    ridges
    0.83
    Act Density 0.015%

    No Known Activations