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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal and organizational structures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     con
    -0.60
     “
    -0.60
     ‘
    -0.59
     em
    -0.59
     &
    -0.59
     char
    -0.58
     ce
    -0.58
    Пе
    -0.58
     de
    -0.57
     Mi
    -0.57
    POSITIVE LOGITS
     excru
    1.65
     ftu
    1.62
     !...
    1.61
     ?...
    1.60
     fatis
    1.58
     perfet
    1.57
     inev
    1.57
     tranf
    1.54
     napoli
    1.54
     lidl
    1.53
    Act Density 0.087%

    No Known Activations