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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal defenses in court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enfans
    -0.58
     spéciaux
    -0.54
     Bewohner
    -0.54
     Stadtteil
    -0.52
     spéciale
    -0.51
     prêtres
    -0.50
     Zeugen
    -0.49
     Mischung
    -0.48
     financières
    -0.48
     Aufla
    -0.48
    POSITIVE LOGITS
     implicit
    0.70
     domain
    0.67
     Implicit
    0.64
     CURIAM
    0.62
     defense
    0.60
     defence
    0.59
     Explicit
    0.59
     nas
    0.58
     uniquely
    0.58
     explicit
    0.57
    Act Density 0.221%

    No Known Activations