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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the contents of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "contents."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äĩ
    -0.74
    ansson
    -0.73
     Rapp
    -0.64
     arri
    -0.64
    eday
    -0.63
    verbs
    -0.63
    roads
    -0.62
    asio
    -0.61
     Siem
    -0.61
     Humph
    -0.60
    POSITIVE LOGITS
     contents
    0.98
    matter
    0.90
    ious
    0.86
     Contents
    0.81
    iveness
    0.81
     thereof
    0.78
    afety
    0.77
    hip
    0.76
    uggest
    0.75
    âĸĪ
    0.74
    Act Density 0.020%

    No Known Activations