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

    Neuronpedia

    INDEX
    Explanations

    information about notable people, including their biographical details and accomplishments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rium
    -0.80
    acceptable
    -0.77
    rians
    -0.73
    react
    -0.72
    ria
    -0.71
     unanim
    -0.70
    enario
    -0.70
    aptic
    -0.68
    uers
    -0.67
    valid
    -0.67
    POSITIVE LOGITS
     stint
    1.29
     Married
    1.12
     married
    1.09
     bachelor
    1.03
     befriend
    1.01
     graduated
    1.01
     lifelong
    1.00
     fluent
    0.98
     graduate
    0.96
     founding
    0.95
    Act Density 9.276%

    No Known Activations