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

    Neuronpedia

    INDEX
    Explanations

    words related to packaging

    oai_token-act-pair · gpt-3.5-turbo

    references to packaging materials and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shire
    -1.06
    nesota
    -0.80
    otos
    -0.79
    inite
    -0.77
     Metatron
    -0.73
    bia
    -0.71
    iscopal
    -0.71
    uable
    -0.70
    frey
    -0.69
    ibur
    -0.68
    POSITIVE LOGITS
     packaging
    0.99
    eers
    0.80
     containers
    0.75
     crates
    0.73
     materials
    0.70
     goods
    0.70
     wrap
    0.70
     packets
    0.67
     coat
    0.65
     shelves
    0.65
    Act Density 0.026%

    No Known Activations