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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "double" in a context that suggests a comparison or duplication

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to "double" and its various contexts, particularly in numerical or descriptive settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zar
    -0.77
     Rica
    -0.76
    çīĪ
    -0.75
     Lauder
    -0.70
     Ud
    -0.68
    ORK
    -0.66
     Mechdragon
    -0.65
    zsche
    -0.65
     TODAY
    -0.63
     Guru
    -0.63
    POSITIVE LOGITS
    sized
    1.22
    edged
    1.19
    digit
    1.02
    tailed
    1.02
    function
    1.02
    sided
    1.01
    handed
    1.00
    headed
    1.00
    length
    1.00
    level
    0.97
    Act Density 0.066%

    No Known Activations