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

    Neuronpedia

    INDEX
    Explanations

    references to presidential approval ratings and historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ault
    -0.18
    hoc
    -0.17
    GRES
    -0.17
    alendar
    -0.17
    posables
    -0.17
    alty
    -0.16
    obo
    -0.15
    alc
    -0.15
    tim
    -0.15
     кÑĥп
    -0.15
    POSITIVE LOGITS
     similarly
    0.16
    agara
    0.16
     offline
    0.15
    icias
    0.15
    é¾
    0.14
     Mas
    0.14
    ä¸įå¾Ĺ
    0.14
    Lorem
    0.14
    pillar
    0.14
     enumerable
    0.13
    Act Density 0.401%

    No Known Activations