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

    Neuronpedia

    INDEX
    Explanations

    specific phrases related to actions, instructions, or proposals concerning projects and initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -1.04
     EconPapers
    -1.03
    Datuak
    -0.96
     الحره
    -0.88
     nahilalakip
    -0.87
    GEBURTSDATUM
    -0.86
     cherchés
    -0.85
     تضيفلها
    -0.84
    LEncoder
    -0.82
     Normdatei
    -0.82
    POSITIVE LOGITS
     which
    0.52
     ordin
    0.43
    Descriptor
    0.41
    which
    0.41
     actively
    0.41
     dedic
    0.40
     designed
    0.40
    ho
    0.39
     lo
    0.39
    med
    0.38
    Act Density 0.317%

    No Known Activations