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

    Neuronpedia

    INDEX
    Explanations

    indicators of system prompts or commands in structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apimachinery
    -0.82
    GEBURTSDATUM
    -0.72
     незавершена
    -0.72
    MemoryWarning
    -0.70
     تضيفلها
    -0.68
    Искәрмәләр
    -0.68
     виправивши
    -0.67
     <<<<<<<<<<<<<<
    -0.67
    出版年
    -0.67
    transQ
    -0.67
    POSITIVE LOGITS
     <=",
    0.57
     الحره
    0.54
     roligt
    0.46
     falso
    0.44
     aikaa
    0.43
    度的
    0.43
    éal
    0.43
    
    0.42
     qualcuno
    0.42
    blico
    0.41
    Act Density 0.141%

    No Known Activations