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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to crime and violations of laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dieux
    -1.01
     bienfaits
    -0.87
     critères
    -0.85
     pères
    -0.79
     vérit
    -0.79
     modalités
    -0.78
     épaules
    -0.78
     vœux
    -0.77
     travailleurs
    -0.77
     âmes
    -0.77
    POSITIVE LOGITS
     trips
    1.43
     visits
    1.35
     searches
    1.23
     encounters
    1.22
     transactions
    1.21
     outings
    1.18
     meetings
    1.18
     sessions
    1.15
     journeys
    1.15
     attacks
    1.13
    Act Density 2.506%

    No Known Activations