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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate adherence or compliance to rules, traditions, or advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.60
     gius
    -0.52
     questione
    -0.50
     potest
    -0.48
     consigo
    -0.48
     partea
    -0.47
     giuri
    -0.46
     particulières
    -0.45
    findpost
    -0.45
    üstü
    -0.45
    POSITIVE LOGITS
     tradition
    0.97
     guidelines
    0.95
     principles
    0.93
     recommendations
    0.90
     principle
    0.88
     instructions
    0.87
     trends
    0.85
     traditions
    0.81
     trend
    0.81
     dictates
    0.81
    Act Density 0.477%

    No Known Activations