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

    Neuronpedia

    INDEX
    Explanations

    important decisions or actions being taken

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to decisions and requests in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cups
    -0.81
    tics
    -0.79
    ernels
    -0.77
    ses
    -0.75
     Empires
    -0.73
     Occupations
    -0.71
     Machines
    -0.70
    rogens
    -0.69
    itudes
    -0.69
    artifacts
    -0.66
    POSITIVE LOGITS
     aimed
    0.74
     called
    0.73
    urring
    0.71
    urrence
    0.70
     involving
    0.69
    atical
    0.68
     Called
    0.67
     akin
    0.67
    aton
    0.66
    jam
    0.66
    Act Density 0.418%

    No Known Activations