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

    Neuronpedia

    INDEX
    Explanations

    numbers and special characters in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data or statistics related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.74
     citiz
    -0.68
    ¥ŀ
    -0.66
    etheless
    -0.64
     volunt
    -0.64
     pacif
    -0.63
     prosec
    -0.58
     chewing
    -0.56
     neigh
    -0.56
     courier
    -0.54
    POSITIVE LOGITS
    Contents
    1.11
    WASHINGTON
    1.02
    Yesterday
    1.00
    Introduction
    0.97
    ³³³³³³³³³³³³³³³³
    0.95
    ³³³³³³³³
    0.93
    Specifically
    0.92
    Recent
    0.91
    Ever
    0.89
    ³³³³
    0.89
    Act Density 0.355%

    No Known Activations