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

    Neuronpedia

    INDEX
    Explanations

    phrases that express critiques or discussions about government and society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eya
    -0.18
    rush
    -0.16
    rega
    -0.15
    berapa
    -0.15
     reck
    -0.15
     reckon
    -0.14
    onces
    -0.14
     World
    -0.14
    bara
    -0.14
     prez
    -0.13
    POSITIVE LOGITS
    esson
    0.16
     semiclass
    0.15
     nackte
    0.15
     åĨĨ
    0.15
     grav
    0.15
    steller
    0.14
     citiz
    0.14
    ÙĤد
    0.14
    ovat
    0.14
    -unstyled
    0.13
    Act Density 0.018%

    No Known Activations