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

    Neuronpedia

    INDEX
    Explanations

    words related to computer hardware processing calculations and performance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    icipated
    -0.73
    MAP
    -0.73
     Franç
    -0.68
     falsehood
    -0.67
     Misty
    -0.66
    é¾įå
    -0.65
     misinformation
    -0.65
    icted
    -0.64
    riad
    -0.64
     Christy
    -0.64
    POSITIVE LOGITS
    pel
    1.03
    ming
    0.94
    iple
    0.91
    atial
    0.91
    emate
    0.89
    eways
    0.88
    atism
    0.88
    packages
    0.87
    pler
    0.87
    rencies
    0.86
    Act Density 0.014%

    No Known Activations