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

    Neuronpedia

    INDEX
    Explanations

    words related to security, investigations, and substances like ricin

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    cassert
    -0.81
    stdarg
    -0.65
     levier
    -0.60
    Și
    -0.58
     kutumia
    -0.58
    Dziękuję
    -0.57
    iomanip
    -0.57
     delà
    -0.53
     pymysql
    -0.52
     Thine
    -0.51
    POSITIVE LOGITS
     list
    0.94
     cammin
    0.93
     suon
    0.92
     centrif
    0.85
     tramont
    0.84
     sappi
    0.82
     spont
    0.82
     soggior
    0.80
     ideolog
    0.80
     notor
    0.80
    Act Density 0.358%

    No Known Activations