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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "said"

    oai_token-act-pair · gpt-3.5-turbo

    instances of reporting or quoting information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ajo
    -0.93
    anu
    -0.75
    ments
    -0.70
    ental
    -0.68
    otin
    -0.65
     renters
    -0.64
    imar
    -0.63
    ription
    -0.62
    atton
    -0.62
    MENT
    -0.61
    POSITIVE LOGITS
    ãĥ¼ãĥĨ
    0.79
    è¦ļéĨĴ
    0.76
     âĨij
    0.66
    Override
    0.65
    ij士
    0.65
     Incarn
    0.64
    escription
    0.63
    ynamic
    0.62
     incidentally
    0.62
     Topic
    0.62
    Act Density 0.101%

    No Known Activations