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

    Neuronpedia

    INDEX
    Explanations

    terms related to technology and business operations

    oai_token-act-pair · gpt-3.5-turbo

    economic terms related to regulations and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WAR
    -0.50
    ggle
    -0.47
     Different
    -0.46
    ZI
    -0.46
    urgical
    -0.46
    bernatorial
    -0.46
     Leaders
    -0.45
     Governors
    -0.45
    hib
    -0.44
    Newsletter
    -0.44
    POSITIVE LOGITS
     notwithstanding
    0.62
    conservancy
    0.60
    ãĥ³ãĤ¸
    0.59
     comprom
    0.54
    ãĥĦ
    0.49
     è£ıè
    0.49
     srf
    0.47
    ãĥ¥
    0.47
    ãĥĩãĤ£
    0.47
    =#
    0.46
    Act Density 3.534%

    No Known Activations