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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "prototype"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prototypes or prototype versions of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leans
    -0.86
    olulu
    -0.81
    die
    -0.80
    query
    -0.78
    don
    -0.76
    andra
    -0.74
    itudes
    -0.73
    words
    -0.73
    nuts
    -0.71
    vation
    -0.70
    POSITIVE LOGITS
     prototype
    1.05
     prototypes
    1.02
     Prototype
    0.84
    hesis
    0.81
     kits
    0.81
     sketches
    0.79
     kit
    0.78
    smanship
    0.76
     mock
    0.76
     sketch
    0.75
    Act Density 0.052%

    No Known Activations