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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     parteci
    -0.53
    出版年
    -0.52
    vieve
    -0.48
     excused
    -0.46
    expandindo
    -0.46
     selve
    -0.44
    Коро
    -0.43
     participação
    -0.43
     individuel
    -0.43
     pierde
    -0.42
    POSITIVE LOGITS
     policies
    0.92
     predecessor
    0.88
     reforms
    0.85
     revital
    0.83
    AndEndTag
    0.81
     oversaw
    0.80
     Policies
    0.80
     restructuring
    0.77
     succeeded
    0.76
     reform
    0.75
    Act Density 0.279%

    No Known Activations