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

    Neuronpedia

    INDEX
    Explanations

    mentions of beliefs related to religious or scientific views

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     kram
    -0.87
     solidar
    -0.74
     zyn
    -0.74
     uhr
    -0.73
     durs
    -0.73
     hina
    -0.72
     ohr
    -0.67
     lemp
    -0.67
     mme
    -0.67
     kano
    -0.66
    POSITIVE LOGITS
     trône
    0.61
     Existen
    0.54
     Février
    0.54
     berço
    0.52
     oiseau
    0.52
     noël
    0.51
     Tienen
    0.51
     ziua
    0.50
     rocher
    0.49
     curé
    0.48
    Act Density 0.572%

    No Known Activations