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

    Neuronpedia

    INDEX
    Explanations

    references to monitoring activities and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    publique
    -0.67
    yargs
    -0.65
     CreateTagHelper
    -0.63
    GeneratedValue
    -0.59
    ΕΣ
    -0.58
    ftagPool
    -0.57
     Waugh
    -0.57
     Klee
    -0.57
    kraft
    -0.56
     fato
    -0.56
    POSITIVE LOGITS
     monitor
    2.98
     monitoring
    2.88
     monitors
    2.83
     Monitor
    2.71
     Monitoring
    2.65
     MONITOR
    2.63
     Monitors
    2.59
    monitor
    2.58
    Monitor
    2.54
    monitoring
    2.52
    Act Density 0.055%

    No Known Activations