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

    Neuronpedia

    INDEX
    Explanations

    mentions of high-ranking officials being investigated or suspended

    oai_token-act-pair · gpt-3.5-turbo

    instances of personnel changes and suspensions within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     legalize
    -0.71
     Ragnarok
    -0.70
    lag
    -0.70
     vict
    -0.70
     Columb
    -0.69
     conquer
    -0.69
     paradise
    -0.69
    é»Ĵ
    -0.68
     backyard
    -0.68
     aven
    -0.68
    POSITIVE LOGITS
     overseeing
    1.14
     resigned
    1.06
     appointed
    1.03
     supervisors
    1.00
     desks
    0.99
     advising
    0.98
     tasked
    0.98
     resign
    0.98
    office
    0.97
     briefed
    0.94
    Act Density 1.244%

    No Known Activations