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

    Neuronpedia

    INDEX
    Explanations

    phrases related to current events and political issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    minster
    -0.70
    pora
    -0.65
    pering
    -0.64
    İĭ
    -0.64
    adem
    -0.64
    QL
    -0.62
    FN
    -0.62
    mage
    -0.61
     footprint
    -0.61
    untarily
    -0.61
    POSITIVE LOGITS
     yeah
    1.12
     guess
    1.04
     maybe
    0.95
     yes
    0.94
     uh
    0.93
    yeah
    0.93
     luckily
    0.91
     congr
    0.90
     fortunately
    0.88
     hello
    0.86
    Act Density 0.047%

    No Known Activations