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

    Neuronpedia

    INDEX
    Explanations

    phrases related to living arrangements and moving in with others

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     provato
    -0.62
     resear
    -0.61
     istr
    -0.55
     erad
    -0.55
     sclero
    -0.54
     contex
    -0.54
     sentito
    -0.53
     upvoted
    -0.53
     rispondere
    -0.53
     pensato
    -0.53
    POSITIVE LOGITS
     Jusqu
    0.76
     Toujours
    0.72
     Leurs
    0.68
     Malgré
    0.65
     Mère
    0.63
     Quelques
    0.61
    AndEndTag
    0.61
     roommates
    0.59
     churrasco
    0.59
    marginVertical
    0.58
    Act Density 0.260%

    No Known Activations