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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal agreements or government actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    aukee
    -0.71
    ument
    -0.69
     Begins
    -0.68
     Papers
    -0.65
    auga
    -0.65
     Retrieved
    -0.61
    ibia
    -0.59
    apest
    -0.57
    jri
    -0.57
    aturdays
    -0.57
    POSITIVE LOGITS
    neath
    1.19
    pins
    1.11
    stood
    1.05
    written
    1.02
    whelming
    1.01
    dogs
    1.00
    lie
    1.00
    lining
    1.00
    writing
    0.99
    lined
    0.99
    Act Density 2.858%

    No Known Activations