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

    Neuronpedia

    INDEX
    Explanations

    words related to consistency or typicality

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     solidar
    -0.89
     ideolog
    -0.88
     kram
    -0.88
     erd
    -0.83
     robus
    -0.83
     makro
    -0.82
     utop
    -0.79
     ohr
    -0.79
     paus
    -0.77
     gesta
    -0.77
    POSITIVE LOGITS
     paradiso
    0.64
     fidèles
    0.64
     chrétiens
    0.62
     dovr
    0.61
     compagn
    0.60
     fameux
    0.57
     appartamento
    0.57
     prêtres
    0.57
     tempio
    0.57
     bénéfice
    0.56
    Act Density 0.285%

    No Known Activations