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

    Neuronpedia

    INDEX
    Explanations

    words related to intellectual property, specifically patents

    oai_token-act-pair · gpt-3.5-turbo

    references to patents and patent applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Revel
    -0.70
     Isles
    -0.69
     Lans
    -0.66
    atan
    -0.64
    de
    -0.64
    ashington
    -0.64
    ombies
    -0.63
    hani
    -0.63
     Boh
    -0.62
    htar
    -0.62
    POSITIVE LOGITS
     infringement
    0.96
    enced
    0.87
    onomy
    0.81
     portfolio
    0.81
    ulent
    0.79
     examiner
    0.77
    ability
    0.76
     patent
    0.73
    encing
    0.73
    ificate
    0.72
    Act Density 0.020%

    No Known Activations