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

    Neuronpedia

    INDEX
    Explanations

    countries and people's names

    oai_token-act-pair · gpt-3.5-turbo

    names of countries, people, or organizations involved in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adobe
    -0.79
    buquerque
    -0.64
     Aub
    -0.59
     Ambro
    -0.59
     Becky
    -0.57
     Ung
    -0.57
     Osc
    -0.55
    Joy
    -0.55
     Earn
    -0.55
    /
    -0.54
    POSITIVE LOGITS
     alike
    1.77
     respectively
    1.13
     together
    0.90
     combined
    0.84
     jointly
    0.81
     versa
    0.80
    together
    0.76
     separately
    0.75
     insepar
    0.75
     combine
    0.74
    Act Density 0.390%

    No Known Activations