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

    Neuronpedia

    INDEX
    Explanations

    courts, judgments, and legal cases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     nutella
    -0.92
     tupperware
    -0.86
     purée
    -0.79
     polenta
    -0.76
     bonbons
    -0.68
     hairc
    -0.68
    Spinach
    -0.67
    Może
    -0.67
     sprigs
    -0.65
     cushi
    -0.64
    POSITIVE LOGITS
     kasa
    1.04
     Amerik
    0.94
     silikon
    0.93
     Teks
    0.91
     induk
    0.88
     panik
    0.87
     duk
    0.87
     Ukraina
    0.85
     kaos
    0.84
     akut
    0.84
    Act Density 0.135%

    No Known Activations