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

    Neuronpedia

    INDEX
    Explanations

    ages or periods of time denoted by numbers followed by "year-old"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of paragraph markers or section breaks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     proport
    -1.01
     enthusi
    -0.99
     conduc
    -0.96
     tiss
    -0.93
     conclud
    -0.92
     referen
    -0.90
     unbeliev
    -0.86
     occas
    -0.86
    Þ
    -0.83
     millenn
    -0.81
    POSITIVE LOGITS
    old
    1.75
    olds
    1.47
    older
    1.21
    OLD
    1.19
    Old
    1.11
    young
    1.10
    long
    1.06
    daughter
    1.02
    tall
    0.94
    alias
    0.93
    Act Density 0.027%

    No Known Activations