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

    Neuronpedia

    INDEX
    Explanations

    phrases related to policy and government decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    undai
    -0.72
    oud
    -0.72
    roit
    -0.71
    apan
    -0.69
    yan
    -0.69
    ebin
    -0.69
    izons
    -0.68
    odox
    -0.68
     troubles
    -0.68
    leased
    -0.67
    POSITIVE LOGITS
     namely
    1.02
     Provided
    1.02
     Stories
    0.76
     Whereas
    0.75
     Firstly
    0.75
     Countries
    0.74
     Machines
    0.73
     Journals
    0.73
     According
    0.73
     Anyone
    0.72
    Act Density 0.144%

    No Known Activations